{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T07:19:44Z","timestamp":1770103184864,"version":"3.49.0"},"reference-count":335,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T00:00:00Z","timestamp":1769990400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T00:00:00Z","timestamp":1769990400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cluster Comput"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1007\/s10586-025-05891-z","type":"journal-article","created":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T18:42:39Z","timestamp":1770057759000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["The rise of hallucination in large language models: systematic reviews, performance analysis and challenges"],"prefix":"10.1007","volume":"29","author":[{"given":"Shamsu","family":"Abdullahi","sequence":"first","affiliation":[]},{"given":"Kamaluddeen Usman","family":"Danyaro","sequence":"additional","affiliation":[]},{"given":"Haruna","family":"Chiroma","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,2,2]]},"reference":[{"key":"5891_CR1","doi-asserted-by":"crossref","unstructured":"Zhu, D. et al.: PoLLMgraph: Unraveling hallucinations in large language models via state transition dynamics. arXiv preprint arXiv:2404.04722, (2024)","DOI":"10.18653\/v1\/2024.findings-naacl.294"},{"issue":"3","key":"5891_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3641289","volume":"15","author":"Y Chang","year":"2024","unstructured":"Chang, Y., et al.: A survey on evaluation of large language models. ACM Trans. Intell. Syst. Technol. 15(3), 1\u201345 (2024)","journal-title":"ACM Trans. Intell. Syst. Technol."},{"issue":"10s","key":"5891_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3505244","volume":"54","author":"S Khan","year":"2022","unstructured":"Khan, S., et al.: Transformers in vision: a survey. ACM comput. Surv. (CSUR) 54(10s), 1\u201341 (2022)","journal-title":"ACM comput. Surv. (CSUR)"},{"key":"5891_CR4","unstructured":"Huang, Y., et al.: Advancing transformer architecture in long-context large language models: A comprehensive survey. arXiv preprint arXiv:2311.12351, (2023)"},{"key":"5891_CR5","unstructured":"Liu, Y., et al.: Understanding llms: A comprehensive overview from training to inference. arXiv preprint arXiv:2401.02038, (2024)"},{"key":"5891_CR6","unstructured":"Liua, Y., et al.: Understanding LLM\u2019s: Comprehensive overview."},{"key":"5891_CR7","unstructured":"Bacciu, A., et al.: Rraml: Reinforced retrieval augmented machine learning. Preprint. arXiv preprint arXiv:2307.12798 (2023)"},{"key":"5891_CR8","unstructured":"Liu, F., et al.: Exploring and evaluating hallucinations in llm-powered code generation. arXiv preprint arXiv:2404.00971 (2024)"},{"key":"5891_CR9","unstructured":"Tonmoy, S., et al.: A comprehensive survey of hallucination mitigation techniques in large language models. arXiv preprint arXiv:2401.01313 (2024)"},{"issue":"1","key":"5891_CR10","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s10916-023-01925-4","volume":"47","author":"M Cascella","year":"2023","unstructured":"Cascella, M., et al.: Evaluating the feasibility of ChatGPT in healthcare: an analysis of multiple clinical and research scenarios. J. Med. Syst. 47(1), 33 (2023)","journal-title":"J. Med. Syst."},{"key":"5891_CR11","doi-asserted-by":"crossref","unstructured":"Spangher, A., et al: Do llms plan like human writers? comparing journalist coverage of press releases with llms. in Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.1216"},{"key":"5891_CR12","doi-asserted-by":"publisher","DOI":"10.1109\/access.2025.3533217","author":"M Siino","year":"2025","unstructured":"Siino, M., et al.: Exploring LLMs applications in law: a literature review on current legal NLP approaches. IEEE Access (2025). https:\/\/doi.org\/10.1109\/access.2025.3533217","journal-title":"IEEE Access"},{"issue":"6","key":"5891_CR13","first-page":"1","volume":"18","author":"J Yang","year":"2024","unstructured":"Yang, J., et al.: Harnessing the power of llms in practice: a survey on chatgpt and beyond. ACM Trans. Knowl. Discov. Data 18(6), 1\u201332 (2024)","journal-title":"ACM Trans. Knowl. Discov. Data"},{"key":"5891_CR14","unstructured":"Luo, J., et al.: Hallucination detection and hallucination mitigation: An investigation. arXiv preprint arXiv:2401.08358, (2024)"},{"key":"5891_CR15","unstructured":"Liu, H., et al.: A survey on hallucination in large vision-language models. arXiv preprint arXiv:2402.00253, (2024)"},{"issue":"12","key":"5891_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3571730","volume":"55","author":"Z Ji","year":"2023","unstructured":"Ji, Z., et al.: Survey of hallucination in natural language generation. ACM Computing Surveys 55(12), 1\u201338 (2023)","journal-title":"ACM Computing Surveys"},{"key":"5891_CR17","doi-asserted-by":"crossref","unstructured":"Chakraborty, N., M. Ornik, K.: Driggs-campbell: hallucination detection in foundation models for decision-making: a flexible definition and review of the state of the art. arXiv preprint arXiv:2403.16527, (2024)","DOI":"10.1145\/3716846"},{"key":"5891_CR18","unstructured":"Ye, H., et al.: Cognitive mirage: A review of hallucinations in large language models. arXiv preprint arXiv:2309.06794, (2023)"},{"key":"5891_CR19","unstructured":"Jiang, X., et al.: A survey on large language model hallucination via a creativity perspective. arXiv preprint arXiv:2402.06647, (2024)"},{"issue":"9","key":"5891_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10462-024-10896-y","volume":"57","author":"Z Lin","year":"2024","unstructured":"Lin, Z., et al.: Towards trustworthy LLMs: a review on debiasing and dehallucinating in large language models. Artificial Intelligence Review 57(9), 1\u201350 (2024)","journal-title":"Artificial Intelligence Review"},{"issue":"8","key":"5891_CR21","doi-asserted-by":"publisher","first-page":"852","DOI":"10.1038\/s42256-024-00881-z","volume":"6","author":"I Augenstein","year":"2024","unstructured":"Augenstein, I., et al.: Factuality challenges in the era of large language models and opportunities for fact-checking. Nature Machine Intelligence 6(8), 852\u2013863 (2024)","journal-title":"Nature Machine Intelligence"},{"key":"5891_CR22","unstructured":"Wang, C., et al.: Survey on factuality in large language models: Knowledge, retrieval and domain-specificity. arXiv preprint arXiv:2310.07521, (2023)"},{"key":"5891_CR23","doi-asserted-by":"publisher","DOI":"10.1145\/3744238","author":"O Shorinwa","year":"2025","unstructured":"Shorinwa, O., et al.: A survey on uncertainty quantification of large language models: Taxonomy, open research challenges, and future directions. ACM Computing Surveys (2025). https:\/\/doi.org\/10.1145\/3744238","journal-title":"ACM Computing Surveys"},{"key":"5891_CR24","unstructured":"Huang, L., et al.: A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. arXiv preprint arXiv:2311.05232, (2023)"},{"issue":"4","key":"5891_CR25","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1016\/j.jss.2006.07.009","volume":"80","author":"P Brereton","year":"2007","unstructured":"Brereton, P., et al.: Lessons from applying the systematic literature review process within the software engineering domain. J. Syst. Softw. 80(4), 571\u2013583 (2007)","journal-title":"J. Syst. Softw."},{"key":"5891_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2024.102068","author":"SM Al-Selwi","year":"2024","unstructured":"Al-Selwi, S.M., et al.: RNN-LSTM: From applications to modeling techniques and beyond\u2014systematic review. J. King Saud Univ. (2024). https:\/\/doi.org\/10.1016\/j.jksuci.2024.102068","journal-title":"J. King Saud Univ."},{"key":"5891_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.109569","volume":"185","author":"SU Hassan","year":"2025","unstructured":"Hassan, S.U., et al.: Local interpretable model-agnostic explanation approach for medical imaging analysis: a systematic literature review. Comput. Biol. Med. 185, 109569 (2025)","journal-title":"Comput. Biol. Med."},{"key":"5891_CR28","unstructured":"Yao, J.-Y., et al.: Llm lies: Hallucinations are not bugs, but features as adversarial examples. arXiv preprint arXiv:2310.01469, (2023)"},{"key":"5891_CR29","unstructured":"Keele, S.: Guidelines for performing systematic literature reviews in software engineering. Technical report, ver. 2.3 ebse technical report. ebse. (2007)"},{"key":"5891_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.infsof.2015.03.007","volume":"64","author":"K Petersen","year":"2015","unstructured":"Petersen, K., Vakkalanka, S., Kuzniarz, L.: Guidelines for conducting systematic mapping studies in software engineering: an update. Information and Software Technology 64, 1\u201318 (2015)","journal-title":"Information and Software Technology"},{"key":"5891_CR31","unstructured":"Hu, T. and Zhou, X.-H.: Unveiling LLM evaluation focused on metrics: challenges and solutions. arXiv preprint arXiv:2404.09135, (2024)"},{"issue":"8","key":"5891_CR32","doi-asserted-by":"publisher","first-page":"5407","DOI":"10.1007\/s41870-024-02205-1","volume":"16","author":"R Tharaniya sairaj","year":"2024","unstructured":"Tharaniya sairaj, R., Balasundaram, S.: Reducing tail entity hallucinations with dependency edge prediction in text to text transfer transformer based auto-generated questions. International Journal of Information Technology 16(8), 5407\u20135419 (2024)","journal-title":"International Journal of Information Technology"},{"key":"5891_CR33","doi-asserted-by":"crossref","unstructured":"Dhuliawala, S., et al.: Chain-of-verification reduces hallucination in large language models. arXiv preprint arXiv:2309.11495, (2023)","DOI":"10.18653\/v1\/2024.findings-acl.212"},{"key":"5891_CR34","doi-asserted-by":"publisher","DOI":"10.1177\/15705838251343009","author":"R Tharaniya Sairaj","year":"2025","unstructured":"Tharaniya Sairaj, R., Balasundaram, S.: Ontology mapping for retrieval augmented modelling to reduce factual hallucinations in pretrained language model-based auto-generated questions. Applied Ontology (2025). https:\/\/doi.org\/10.1177\/15705838251343009","journal-title":"Applied Ontology"},{"key":"5891_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, C., et al: Prefer: Prompt ensemble learning via feedback-reflect-refine. In: Proceedings of the AAAI Conference on Artificial Intelligence. (2024)","DOI":"10.1609\/aaai.v38i17.29924"},{"key":"5891_CR36","unstructured":"Bang, Y., et al.: A multitask, multilingual, multimodal evaluation of chatgpt on reasoning, hallucination, and interactivity. arXiv preprint arXiv:2302.04023, (2023)"},{"key":"5891_CR37","volume-title":"2023 IEEE international conference on big data (BigData)","author":"K Boros","year":"2023","unstructured":"Boros, K., Oyamada, M.: towards large language model organization: a case study on abstractive summarization. In: 2023 IEEE international conference on big data (BigData). IEEE (2023)"},{"key":"5891_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, W., et al.: Towards fine-grained citation evaluation in generated text: A comparative analysis of faithfulness metrics. arXiv preprint arXiv:2406.15264, (2024)","DOI":"10.18653\/v1\/2024.inlg-main.35"},{"key":"5891_CR39","unstructured":"Kang, H., T. Blevins, and L. Zettlemoyer: Comparing hallucination detection metrics for multilingual generation. arXiv preprint arXiv:2402.10496, (2024)"},{"key":"5891_CR40","unstructured":"Vaswani, A.: Attention is all you need. arXiv preprint arXiv:1706.03762, (2017)"},{"key":"5891_CR41","doi-asserted-by":"crossref","unstructured":"Maynez, J., et al.: On faithfulness and factuality in abstractive summarization. arXiv preprint arXiv:2005.00661, (2020)","DOI":"10.18653\/v1\/2020.acl-main.173"},{"key":"5891_CR42","doi-asserted-by":"crossref","unstructured":"Han, W., H. Zhao, and Z. Cai: Empowering multimodal models\u2019 in-context learning ability through large language models. In: Proceedings of the ACM turing award celebration conference - China 2023. p. 9\u201310 (2024)","DOI":"10.1145\/3603165.3607368"},{"key":"5891_CR43","doi-asserted-by":"publisher","DOI":"10.1109\/access.2024.3365742","author":"MAK Raiaan","year":"2024","unstructured":"Raiaan, M.A.K., et al.: A review on large language models: architectures, applications, taxonomies, open issues and challenges. IEEE Access (2024). https:\/\/doi.org\/10.1109\/access.2024.3365742","journal-title":"IEEE Access"},{"key":"5891_CR44","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Evaluating object hallucination in large vision-language models. arXiv preprint arXiv:2305.10355, (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"5891_CR45","doi-asserted-by":"crossref","unstructured":"Manakul, P., A. Liusie, and M.J. Gales, Selfcheckgpt: Zero-resource black-box hallucination detection for generative large language models. arXiv preprint arXiv:2303.08896, (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.557"},{"key":"5891_CR46","doi-asserted-by":"crossref","unstructured":"Pal, A., L.K. Umapathi, and M. Sankarasubbu: Med-halt: Medical domain hallucination test for large language models. arXiv preprint arXiv:2307.15343, (2023)","DOI":"10.18653\/v1\/2023.conll-1.21"},{"key":"5891_CR47","doi-asserted-by":"crossref","unstructured":"Gunjal, A., Yin, J., Bas, E.: Detecting and preventing hallucinations in large vision language models. in Proceedings of the AAAI Conference on Artificial Intelligence. (2024)","DOI":"10.1609\/aaai.v38i16.29771"},{"key":"5891_CR48","doi-asserted-by":"crossref","unstructured":"Chen, J., et al: Benchmarking large language models in retrieval-augmented generation. in Proceedings of the AAAI Conference on Artificial Intelligence. (2024)","DOI":"10.1609\/aaai.v38i16.29728"},{"key":"5891_CR49","doi-asserted-by":"crossref","unstructured":"Kamalloo, E., et al:, Evaluating open-domain question answering in the era of large language models. arXiv preprint arXiv:2305.06984, (2023)","DOI":"10.18653\/v1\/2023.acl-long.307"},{"key":"5891_CR50","doi-asserted-by":"crossref","unstructured":"Shuster, K., et al.: Retrieval augmentation reduces hallucination in conversation. arXiv preprint arXiv:2104.07567, (2021)","DOI":"10.18653\/v1\/2021.findings-emnlp.320"},{"key":"5891_CR51","doi-asserted-by":"crossref","unstructured":"Ji, Z., et al.: Towards mitigating hallucination in large language models via self-reflection. arXiv preprint arXiv:2310.06271, (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.123"},{"key":"5891_CR52","doi-asserted-by":"crossref","unstructured":"Li, H., et al.: Theory of mind for multi-agent collaboration via large language models. arXiv preprint arXiv:2310.10701, (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.13"},{"key":"5891_CR53","unstructured":"Trivedi, H., et al.: Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions. arXiv preprint arXiv:2212.10509, (2022)"},{"key":"5891_CR54","unstructured":"M\u00fcndler, N., et al.: Self-contradictory hallucinations of large language models: Evaluation, detection and mitigation. arXiv preprint arXiv:2305.15852, (2023)"},{"key":"5891_CR55","doi-asserted-by":"crossref","unstructured":"Leng, S., et al.:Mitigating object hallucinations in large vision-language models through visual contrastive decoding. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. (2024)","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"5891_CR56","unstructured":"Kim, B., et al.: Cartoon Hallucinations detection: Pose-aware in context visual learning. arXiv e-prints, p. arXiv: 2403.15048. (2024)"},{"key":"5891_CR57","doi-asserted-by":"crossref","unstructured":"Shao, Z., et al.: Enhancing retrieval-augmented large language models with iterative retrieval-generation synergy. arXiv preprint arXiv:2305.15294, (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.620"},{"key":"5891_CR58","unstructured":"Chuang, Y.-S., et al.: Dola: Decoding by contrasting layers improves factuality in large language models. arXiv preprint arXiv:2309.03883, (2023)"},{"key":"5891_CR59","unstructured":"Gao, D., et al.: Text-to-sql empowered by large language models: A benchmark evaluation. arXiv preprint arXiv:2308.15363, (2023)"},{"issue":"12","key":"5891_CR60","doi-asserted-by":"publisher","first-page":"220105","DOI":"10.1007\/s11432-024-4251-x","volume":"67","author":"S Yin","year":"2024","unstructured":"Yin, S., et al.: Woodpecker: hallucination correction for multimodal large language models. Sci. China Inf. Sci. 67(12), 220105 (2024)","journal-title":"Sci. China Inf. Sci."},{"key":"5891_CR61","doi-asserted-by":"crossref","unstructured":"Guan, T., et al.: Hallusionbench: an advanced diagnostic suite for entangled language hallucination and visual illusion in large vision-language models. in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. (2024)","DOI":"10.1109\/CVPR52733.2024.01363"},{"key":"5891_CR62","unstructured":"Bhamidipati, P., et al.: Zero-shot multi-task hallucination detection. arXiv preprint arXiv:2403.12244, (2024)"},{"key":"5891_CR63","doi-asserted-by":"crossref","unstructured":"Cao, M., Y. Dong, and J.C.K. Cheung: Hallucinated but factual! inspecting the factuality of hallucinations in abstractive summarization. arXiv preprint arXiv:2109.09784, (2021)","DOI":"10.18653\/v1\/2022.acl-long.236"},{"key":"5891_CR64","doi-asserted-by":"crossref","unstructured":"Zhou, C., et al.: Detecting hallucinated content in conditional neural sequence generation. arXiv preprint arXiv:2011.02593, (2020)","DOI":"10.18653\/v1\/2021.findings-acl.120"},{"key":"5891_CR65","doi-asserted-by":"crossref","unstructured":"Marfurt, A. and J: Henderson. Unsupervised token-level hallucination detection from summary generation by-products. In: Proceedings of the 2nd workshop on natural language generation, evaluation, and metrics (GEM). (2022)","DOI":"10.18653\/v1\/2022.gem-1.21"},{"key":"5891_CR66","doi-asserted-by":"crossref","unstructured":"Rawte, V., et al.: FACTOID: Factual entailment for hallucination detection. arXiv preprint arXiv:2403.19113, (2024)","DOI":"10.18653\/v1\/2025.trustnlp-main.38"},{"key":"5891_CR67","doi-asserted-by":"crossref","unstructured":"Choi, S., et al., KCTS: knowledge-constrained tree search decoding with token-level hallucination detection. arXiv preprint arXiv:2310.09044, (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.867"},{"key":"5891_CR68","unstructured":"Liu, T., et al.: A token-level reference-free hallucination detection benchmark for free-form text generation. arXiv preprint arXiv:2104.08704, (2021)"},{"key":"5891_CR69","doi-asserted-by":"crossref","unstructured":"Xiao, W., et al: Detecting and mitigating hallucination in large vision language models via fine-grained ai feedback. in Proceedings of the AAAI Conference on Artificial Intelligence. (2025)","DOI":"10.1609\/aaai.v39i24.34744"},{"key":"5891_CR70","doi-asserted-by":"crossref","unstructured":"Su, W., et al.: Unsupervised real-time hallucination detection based on the internal states of large language models. arXiv preprint arXiv:2403.06448, (2024)","DOI":"10.18653\/v1\/2024.findings-acl.854"},{"key":"5891_CR71","unstructured":"Rateike, M., et al.: Weakly supervised detection of hallucinations in llm activations. arXiv preprint arXiv:2312.02798, (2023)"},{"key":"5891_CR72","doi-asserted-by":"crossref","unstructured":"Chuang, Y.-S., et al.: Lookback lens: Detecting and mitigating contextual hallucinations in large language models using only attention maps. arXiv preprint arXiv:2407.07071, (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.84"},{"key":"5891_CR73","unstructured":"Suresh, M., et al.\u201d: Towards improving open-box hallucination detection in large language models (LLMs). (2024)"},{"key":"5891_CR74","doi-asserted-by":"crossref","unstructured":"Nonkes, N., et al.: Leveraging graph structures to detect hallucinations in large language models. arXiv preprint arXiv:2407.04485, (2024)","DOI":"10.18653\/v1\/2024.textgraphs-1.7"},{"key":"5891_CR75","doi-asserted-by":"crossref","unstructured":"He, X., et al: Improving factual error correction by learning to inject factual errors. In Proceedings of the AAAI Conference on Artificial Intelligence. (2024)","DOI":"10.1609\/aaai.v38i16.29778"},{"key":"5891_CR76","doi-asserted-by":"crossref","unstructured":"Chen, L., et al: Data race detection using large language models. In: Proceedings of the SC\u201923 Workshops of The international conference on high performance computing, network, storage, and analysis. (2023)","DOI":"10.1145\/3624062.3624088"},{"key":"5891_CR77","doi-asserted-by":"crossref","unstructured":"Borra, F., et al.: Malto at semeval-2024 task 6: Leveraging synthetic data for llm hallucination detection. arXiv preprint arXiv:2403.00964, (2024)","DOI":"10.18653\/v1\/2024.semeval-1.240"},{"key":"5891_CR78","doi-asserted-by":"crossref","unstructured":"Biten, A.F., G\u00f3mez, L., Karatzas, D.: Let there be a clock on the beach: Reducing object hallucination in image captioning. In proceedings of the IEEE\/CVF winter conference on applications of computer vision. (2022)","DOI":"10.1109\/WACV51458.2022.00253"},{"key":"5891_CR79","doi-asserted-by":"crossref","unstructured":"Yu, Q., et al.: Hallucidoctor: Mitigating hallucinatory toxicity in visual instruction data. In: Proceedings of the IEEE\/cvf conference on computer vision and pattern recognition. (2024)","DOI":"10.1109\/CVPR52733.2024.01230"},{"key":"5891_CR80","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Hallucination detection for generative large language models by bayesian sequential estimation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.949"},{"key":"5891_CR81","doi-asserted-by":"crossref","unstructured":"Shang, Z., et al.: Ontofact: Unveiling fantastic fact-skeleton of llms via ontology-driven reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence. (2024)","DOI":"10.1609\/aaai.v38i17.29859"},{"key":"5891_CR82","unstructured":"Varshney, N., et al.: A Stitch in time saves nine: detecting and mitigating hallucinations of LLMs by actively validating low-confidence generation."},{"key":"5891_CR83","volume-title":"2023 International Conference on Machine Learning and Applications (ICMLA)","author":"K Furumai","year":"2023","unstructured":"Furumai, K., et al.: Detecting dialogue hallucination using graph neural networks. In: 2023 International Conference on Machine Learning and Applications (ICMLA). IEEE (2023)"},{"key":"5891_CR84","doi-asserted-by":"crossref","unstructured":"Wu, J., Logical closed loop: uncovering object hallucinations in large vision-language models. arXiv preprint. arXiv preprint arXiv:2402.11622, (2024)","DOI":"10.18653\/v1\/2024.findings-acl.414"},{"key":"5891_CR85","doi-asserted-by":"crossref","unstructured":"Rivera, M., et al.: Combining confidence elicitation and sample-based methods for uncertainty quantification in misinformation mitigation. arXiv preprint arXiv:2401.08694, (2024)","DOI":"10.18653\/v1\/2024.uncertainlp-1.12"},{"key":"5891_CR86","doi-asserted-by":"crossref","unstructured":"Albanese, N.C: In-context learning for scalable and online hallucination detection in RAGS. in CS & IT Conference Proceedings. CS & IT Conference Proceedings. (2024)","DOI":"10.5121\/csit.2024.140703"},{"key":"5891_CR87","doi-asserted-by":"crossref","unstructured":"Maharaj, K., et al.: Eyes show the way: Modelling gaze behaviour for hallucination detection. In Findings of the association for computational linguistics: EMNLP 2023. (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.764"},{"key":"5891_CR88","doi-asserted-by":"crossref","unstructured":"Zhang, T., et al.: Enhancing uncertainty-based hallucination detection with stronger focus. arXiv preprint arXiv:2311.13230, (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.58"},{"key":"5891_CR89","doi-asserted-by":"crossref","unstructured":"Yang, S., R. Sun, and X. Wan: A new benchmark and reverse validation method for passage-level hallucination detection. arXiv preprint arXiv:2310.06498, (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.256"},{"key":"5891_CR90","unstructured":"Sridhar, A.K. and E. Visser, Improved beam search for hallucination mitigation in abstractive summarization. arXiv preprint arXiv:2212.02712, (2022)"},{"key":"5891_CR91","doi-asserted-by":"crossref","unstructured":"Jha, S., et al.: Dehallucinating large language models using formal methods guided iterative prompting. In 2023 IEEE International Conference on Assured Autonomy (ICAA). IEEE. (2023)","DOI":"10.1109\/ICAA58325.2023.00029"},{"key":"5891_CR92","doi-asserted-by":"crossref","unstructured":"Leiser, F., et al.: Hill: A hallucination identifier for large language models. in Proceedings of the CHI Conference on Human Factors in Computing Systems. (2024)","DOI":"10.1145\/3613904.3642428"},{"key":"5891_CR93","doi-asserted-by":"crossref","unstructured":"Uluoglakci, C., Temizel, T.T.: HypoTermQA: Hypothetical terms dataset for benchmarking hallucination tendency of LLMs. arXiv preprint arXiv:2402.16211, (2024)","DOI":"10.18653\/v1\/2024.eacl-srw.9"},{"issue":"10","key":"5891_CR94","doi-asserted-by":"publisher","DOI":"10.3390\/math11102320","volume":"11","author":"M Lee","year":"2023","unstructured":"Lee, M.: A mathematical investigation of hallucination and creativity in gpt models. Mathematics 11(10), 2320 (2023)","journal-title":"Mathematics"},{"key":"5891_CR95","doi-asserted-by":"crossref","unstructured":"Wan, Y., et al.: Kelly is a warm person, Joseph is a role model\u201d: Gender biases in LLM-generated reference letters (arXiv: 2310.09219). arXiv. (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.243"},{"key":"5891_CR96","doi-asserted-by":"crossref","unstructured":"Gatto, J., O. Sharif, and S.M.: Preum, chain-of-thought embeddings for stance detection on social media. arXiv preprint arXiv:2310.19750, (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.273"},{"key":"5891_CR97","doi-asserted-by":"crossref","unstructured":"Shen, J., et al.: \u201cWhy is this misleading?\u201d: Detecting news headline hallucinations with explanations. In: Proceedings of the ACM Web Conference 2023. (2023)","DOI":"10.1145\/3543507.3583375"},{"key":"5891_CR98","unstructured":"Kim, B., et al.: Cartoon hallucinations detection: Pose-aware in context visual learning. arXiv preprint arXiv:2403.15048, (2024)"},{"key":"5891_CR99","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Hallucination detection: Robustly discerning reliable answers in large language models. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. (2023)","DOI":"10.1145\/3583780.3614905"},{"key":"5891_CR100","unstructured":"Zhang, J., et al.: Knowhalu: Hallucination detection via multi-form knowledge based factual checking. arXiv preprint arXiv:2404.02935, (2024)"},{"key":"5891_CR101","doi-asserted-by":"crossref","unstructured":"Su, W., et al.: Mitigating entity-level hallucination in large language models. In: Proceedings of the 2024 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region. (2024)","DOI":"10.1145\/3673791.3698403"},{"key":"5891_CR102","unstructured":"Chen, X., et al.: Unified hallucination detection for multimodal large language models. arXiv preprint arXiv:2402.03190, (2024)"},{"key":"5891_CR103","unstructured":"Mishra, A., et al.: Fine-grained hallucination detection and editing for language models. arXiv preprint arXiv:2401.06855, (2024)"},{"key":"5891_CR104","doi-asserted-by":"crossref","unstructured":"Das, S., S. Saha, and R.K. Srihari: Diving deep into modes of fact hallucinations in dialogue systems. arXiv preprint arXiv:2301.04449, (2023)","DOI":"10.18653\/v1\/2022.findings-emnlp.48"},{"issue":"OOPSLA2","key":"5891_CR105","doi-asserted-by":"publisher","first-page":"1843","DOI":"10.1145\/3689776","volume":"8","author":"N Li","year":"2024","unstructured":"Li, N., et al.: Drowzee: Metamorphic testing for fact-conflicting hallucination detection in large language models. Proc. ACM Program. Lang. 8(OOPSLA2), 1843\u20131872 (2024)","journal-title":"Proc. ACM Program. Lang."},{"key":"5891_CR106","doi-asserted-by":"crossref","unstructured":"Sun, X., et al.: Towards detecting llms hallucination via markov chain-based multi-agent debate framework. In: ICASSP 2025\u20132025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE. (2025)","DOI":"10.1109\/ICASSP49660.2025.10889448"},{"key":"5891_CR107","doi-asserted-by":"crossref","unstructured":"Sheng, J.: An augmentable domain-specific models for financial analysis. In: 2023 16th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI). IEEE. (2023)","DOI":"10.1109\/CISP-BMEI60920.2023.10373245"},{"key":"5891_CR108","doi-asserted-by":"crossref","unstructured":"Agrawal, G., et al.: CyberQ: Generating questions and answers for cybersecurity education using knowledge graph-augmented LLMs. In: Proceedings of the AAAI Conference on Artificial Intelligence. (2024)","DOI":"10.1609\/aaai.v38i21.30362"},{"key":"5891_CR109","doi-asserted-by":"crossref","unstructured":"Du, M., et al.: From static to dynamic: Knowledge metabolism for large language models. In: Proceedings of the AAAI Conference on Artificial Intelligence. (2024)","DOI":"10.1609\/aaai.v38i21.30564"},{"key":"5891_CR110","doi-asserted-by":"crossref","unstructured":"Hang, C.N., P.-D. Yu, and C.W. Tan. TrumorGPT: Query optimization and semantic reasoning over networks for automated fact-checking. In: 2024 58th Annual Conference on Information Sciences and Systems (CISS). IEEE. (2024)","DOI":"10.1109\/CISS59072.2024.10480162"},{"key":"5891_CR111","doi-asserted-by":"crossref","unstructured":"Nguyen, M., et al.: Efficient fine-tuning large language models for knowledge-aware response planning. in Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer. (2023)","DOI":"10.1007\/978-3-031-43415-0_35"},{"key":"5891_CR112","unstructured":"Wan, F., et al.: Mitigating hallucinations of large language models via knowledge consistent alignment. arXiv preprint arXiv:2401.10768, (2024)"},{"key":"5891_CR113","doi-asserted-by":"crossref","unstructured":"Sen, P., S. Mavadia, and A. Saffari.: Knowledge graph-augmented language models for complex question answering. In: Proceedings of the 1st Workshop on Natural Language Reasoning and Structured Explanations (NLRSE). (2023)","DOI":"10.18653\/v1\/2023.nlrse-1.1"},{"key":"5891_CR114","unstructured":"Truong, C., Knowledge injection to counter large language model (LLM) hallucination."},{"key":"5891_CR115","doi-asserted-by":"crossref","unstructured":"Guan, X., et al.: Mitigating large language model hallucinations via autonomous knowledge graph-based retrofitting. In: Proceedings of the AAAI Conference on Artificial Intelligence. (2024)","DOI":"10.1609\/aaai.v38i16.29770"},{"key":"5891_CR116","unstructured":"Niu, M., et al.: Mitigating Hallucinations in Large Language Models via Self-Refinement-Enhanced Knowledge Retrieval. arXiv preprint arXiv:2405.06545, (2024)"},{"key":"5891_CR117","unstructured":"Lommatzsch, A., et al.: Combining information retrieval and large language models for a chatbot that generates reliable, natural-style answers."},{"key":"5891_CR118","doi-asserted-by":"crossref","unstructured":"Dziri, N., et al.: Neural path hunter: Reducing hallucination in dialogue systems via path grounding. arXiv preprint arXiv:2104.08455, (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.168"},{"key":"5891_CR119","doi-asserted-by":"crossref","unstructured":"Xiao, Z., et al.: Instructed language models with retrievers are powerful entity linkers. arXiv preprint arXiv:2311.03250, (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.139"},{"key":"5891_CR120","doi-asserted-by":"crossref","unstructured":"Mondal, D., et al.: Kam-cot: Knowledge augmented multimodal chain-of-thoughts reasoning. in Proceedings of the AAAI Conference on Artificial Intelligence. (2024)","DOI":"10.1609\/aaai.v38i17.29844"},{"key":"5891_CR121","doi-asserted-by":"crossref","unstructured":"Ji, Z., et al.: RHO ($\\rho $): Reducing hallucination in open-domain dialogues with knowledge grounding. arXiv preprint arXiv:2212.01588, (2022)","DOI":"10.18653\/v1\/2023.findings-acl.275"},{"key":"5891_CR122","unstructured":"Lv, Q., et al.: Coarse-to-fine highlighting: Reducing knowledge hallucination in large language models. arXiv preprint arXiv:2410.15116, (2024)"},{"key":"5891_CR123","unstructured":"Mohanty, A.: EduEmbedd-A knowledge graph embedding for education. In: EKG-LLM@ CIKM. (2023)"},{"key":"5891_CR124","doi-asserted-by":"crossref","unstructured":"Wang, C., et al.: Knowledge graphs enhanced large language model prompt for electric power question answering. In: Proceedings of the 2023 7th International Conference on Electronic Information Technology and Computer Engineering. (2023)","DOI":"10.1145\/3650400.3650405"},{"key":"5891_CR125","doi-asserted-by":"crossref","unstructured":"Cirik, V., L.-P. Morency, and T. Berg-Kirkpatrick. Holm: Hallucinating objects with language models for referring expression recognition in partially-observed scenes. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). (2022)","DOI":"10.18653\/v1\/2022.acl-long.373"},{"key":"5891_CR126","doi-asserted-by":"crossref","unstructured":"Wan, F., et al.: Knowledge verification to nip hallucination in the bud. arXiv preprint arXiv:2401.10768, (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.152"},{"key":"5891_CR127","unstructured":"Chen, G., et al. RRHF-V: Ranking responses to mitigate hallucinations in multimodal large language models with human feedback. In Proceedings of the 31st International Conference on Computational Linguistics. (2025)"},{"key":"5891_CR128","unstructured":"Kang, H., Ni, J., Yao, H.: Ever: Mitigating hallucination in large language models through real-time verification and rectification. arXiv preprint arXiv:2311.09114, (2023)"},{"key":"5891_CR129","doi-asserted-by":"crossref","unstructured":"Maragheh, R.Y., et al.: LLM-TAKE: Theme-aware keyword extraction using large language models. In: 2023 IEEE International Conference on Big Data (BigData). IEEE. (2023)","DOI":"10.1109\/BigData59044.2023.10386476"},{"key":"5891_CR130","doi-asserted-by":"crossref","unstructured":"Yu, L., et al.: Melo: Enhancing model editing with neuron-indexed dynamic lora. In: Proceedings of the AAAI Conference on Artificial Intelligence. (2024)","DOI":"10.1609\/aaai.v38i17.29916"},{"key":"5891_CR131","doi-asserted-by":"crossref","unstructured":"Yu, T., Zhang, S., Feng, Y.: Truth-aware context selection: Mitigating hallucinations of large language models being misled by untruthful contexts. arXiv preprint arXiv:2403.07556, (2024)","DOI":"10.18653\/v1\/2024.findings-acl.645"},{"key":"5891_CR132","unstructured":"Choubey, P.K., et al., Cape: Contrastive parameter ensembling for reducing hallucination in abstractive summarization. arXiv preprint arXiv:2110.07166, (2021)"},{"key":"5891_CR133","unstructured":"Kim, J., et al., Re-Ex: Revising after explanation reduces the factual errors in LLM Responses. arXiv preprint arXiv:2402.17097, (2024)"},{"key":"5891_CR134","doi-asserted-by":"crossref","unstructured":"Zhang, S., T. Yu, and Y. Feng, Truthx: Alleviating hallucinations by editing large language models in truthful space. arXiv preprint arXiv:2402.17811, (2024)","DOI":"10.18653\/v1\/2024.acl-long.483"},{"key":"5891_CR135","doi-asserted-by":"crossref","unstructured":"Bouyamourn, A., Why LLMs hallucinate, and how to get (evidential) closure: Perceptual, intensional, and extensional learning for faithful natural language generation. arXiv preprint arXiv:2310.15355, (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.192"},{"key":"5891_CR136","unstructured":"Xia, Y., et al.: Hallucination diversity-aware active learning for text summarization. arXiv preprint arXiv:2404.01588, (2024)"},{"key":"5891_CR137","unstructured":"Ding, H., et al.: Retrieve only when it needs: Adaptive retrieval augmentation for hallucination mitigation in large language models. arXiv preprint arXiv:2402.10612, (2024)"},{"key":"5891_CR138","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: Truth forest: Toward multi-scale truthfulness in large language models through intervention without tuning. in Proceedings of the AAAI Conference on Artificial Intelligence. (2024)","DOI":"10.1609\/aaai.v38i19.30087"},{"key":"5891_CR139","unstructured":"Han, Z., et al.: Skip $\\textbackslash n $: A simple method to reduce hallucination in Large Vision-Language Models. arXiv preprint arXiv:2402.01345, (2024)"},{"key":"5891_CR140","unstructured":"Duan, J., et al.: Shifting attention to relevance: Towards the uncertainty estimation of large language models. arXiv preprint arXiv:2307.01379, (2023)"},{"key":"5891_CR141","doi-asserted-by":"crossref","unstructured":"Huang, Q., et al.: Opera: Alleviating hallucination in multi-modal large language models via over-trust penalty and retrospection-allocation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. (2024)","DOI":"10.1109\/CVPR52733.2024.01274"},{"key":"5891_CR142","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.125723","volume":"263","author":"J Shi","year":"2025","unstructured":"Shi, J., et al.: Mitigating reasoning hallucination through multi-agent collaborative filtering. Expert Systems with Applications 263, 125723 (2025)","journal-title":"Expert Systems with Applications"},{"key":"5891_CR143","unstructured":"Chen, Z., et al., Halc: Object hallucination reduction via adaptive focal-contrast decoding. arXiv preprint arXiv:2403.00425, (2024)"},{"key":"5891_CR144","doi-asserted-by":"crossref","unstructured":"Sun, W., et al.: Contrastive learning reduces hallucination in conversations. in Proceedings of the AAAI Conference on Artificial Intelligence. (2023)","DOI":"10.1609\/aaai.v37i11.26596"},{"key":"5891_CR145","unstructured":"Ramesh, V., Chi, N.A., Rajpurkar, P.: Improving radiology report generation systems by removing hallucinated references to non-existent priors. in Machine Learning for Health. PMLR. (2022)"},{"key":"5891_CR146","doi-asserted-by":"crossref","unstructured":"Wang, B., et al. Vigc: Visual instruction generation and correction. in Proceedings of the AAAI Conference on Artificial Intelligence. (2024)","DOI":"10.1609\/aaai.v38i6.28338"},{"key":"5891_CR147","doi-asserted-by":"crossref","unstructured":"Wu, J., et al., Logical closed loop: Uncovering object hallucinations in large vision-language models. arXiv preprint arXiv:2402.11622, (2024)","DOI":"10.18653\/v1\/2024.findings-acl.414"},{"key":"5891_CR148","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: Mitigating fine-grained hallucination by fine-tuning large vision-language models with caption rewrites. In: International Conference on Multimedia Modeling. Springer. (2024)","DOI":"10.1007\/978-3-031-53302-0_3"},{"key":"5891_CR149","unstructured":"Xiao, W., et al.: Detecting and mitigating hallucination in large vision language models via fine-grained ai feedback. arXiv preprint arXiv:2404.14233, (2024)"},{"key":"5891_CR150","doi-asserted-by":"crossref","unstructured":"Liu, G., et al.: Mitigating Hallucination in Large Language Model by Leveraging Decoder Layer Contrasting. In: International Conference on Pattern Recognition. Springer. (2025)","DOI":"10.1007\/978-3-031-78498-9_4"},{"key":"5891_CR151","doi-asserted-by":"crossref","unstructured":"Waldendorf, J., Haddow, B., Birch, A.: Contrastive Decoding Reduces Hallucinations in Large Multilingual Machine Translation Models. in Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). (2024)","DOI":"10.18653\/v1\/2024.eacl-long.155"},{"key":"5891_CR152","doi-asserted-by":"crossref","unstructured":"Chen, D., et al. Freeze-CD: Alleviating hallucination of large language models via contrastive decoding with local freezing training. In: 2024 IEEE International Conference on Smart Internet of Things (SmartIoT). IEEE, (2024)","DOI":"10.1109\/SmartIoT62235.2024.00056"},{"key":"5891_CR153","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Mitigating hallucinations in large vision-language models with instruction contrastive decoding. arXiv preprint arXiv:2403.18715, (2024)","DOI":"10.18653\/v1\/2024.findings-acl.937"},{"key":"5891_CR154","doi-asserted-by":"crossref","unstructured":"Manevich, A., Tsarfaty, R.: Mitigating Hallucinations in Large Vision-Language Models (LVLMs) via Language-Contrastive Decoding (LCD). arXiv preprint arXiv:2408.04664, (2024)","DOI":"10.18653\/v1\/2024.findings-acl.359"},{"key":"5891_CR155","doi-asserted-by":"crossref","unstructured":"Li, F., Zhang, P.: Mitigating hallucination issues in small-parameter LLMs through inter-layer contrastive decoding. In: 2024 International Joint Conference on Neural Networks (IJCNN). IEEE, (2024)","DOI":"10.1109\/IJCNN60899.2024.10650644"},{"key":"5891_CR156","doi-asserted-by":"crossref","unstructured":"Zhong, W., et al., Investigating and mitigating the multimodal hallucination snowballing in large vision-language models. arXiv preprint arXiv:2407.00569, (2024)","DOI":"10.18653\/v1\/2024.acl-long.648"},{"key":"5891_CR157","unstructured":"Huang, C.P., Chen, H.-Y.: Delta-contrastive decoding mitigates text hallucinations in large language models. arXiv preprint arXiv:2502.05825, (2025)"},{"key":"5891_CR158","unstructured":"Zhang, Y.-F., et al., Debiasing large visual language models. arXiv preprint arXiv:2403.05262, (2024)"},{"key":"5891_CR159","doi-asserted-by":"crossref","unstructured":"McCarthy, A.D., et al. Long-form speech translation through segmentation with finite-state decoding Constraints on large language models. In: Findings of the Association for Computational Linguistics: EMNLP 2023. (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.19"},{"key":"5891_CR160","unstructured":"Liu, H., et al., Visual instruction tuning. Advances in neural information processing systems, 36, (2024)"},{"key":"5891_CR161","doi-asserted-by":"crossref","unstructured":"Chen, Y.-S., et al.: SINC: Self-supervised in-context learning for vision-language tasks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. (2023)","DOI":"10.1109\/ICCV51070.2023.01415"},{"key":"5891_CR162","doi-asserted-by":"crossref","unstructured":"Zhang, H., Liu, X., Zhang, J.: Summit: Iterative text summarization via chatgpt. arXiv preprint arXiv:2305.14835, (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.714"},{"key":"5891_CR163","doi-asserted-by":"crossref","unstructured":"Goyal, S., et al.: Healai: A healthcare llm for effective medical documentation. In: Proceedings of the 17th ACM International Conference on Web Search and Data Mining. (2024)","DOI":"10.1145\/3616855.3635739"},{"key":"5891_CR164","doi-asserted-by":"crossref","unstructured":"Qiu, Y., et al.: Detecting and mitigating hallucinations in multilingual summarisation. arXiv preprint arXiv:2305.13632, (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.551"},{"key":"5891_CR165","doi-asserted-by":"crossref","unstructured":"Shen, J., et al.: Why is this misleading?\u201d: Detecting News Headline Hallucinations with Explanations. In: Proceedings of the ACM Web Conference 2023. p. 1662\u20131672. (2023)","DOI":"10.1145\/3543507.3583375"},{"key":"5891_CR166","unstructured":"Park, D., et al.: Mitigating dialogue hallucination for large multi-modal models via adversarial instruction tuning. arXiv e-prints, p. arXiv: 2403.10492. (2024)"},{"key":"5891_CR167","unstructured":"Tonmoy, S., et al.: A comprehensive survey of hallucination mitigation techniques in large language models. arXiv preprint arXiv:2401.01313, 6, (2024)"},{"key":"5891_CR168","unstructured":"Rawte, V., et al.: Exploring the relationship between llm hallucinations and prompt linguistic nuances: Readability, formality, and concreteness. arXiv preprint arXiv:2309.11064, (2023)"},{"key":"5891_CR169","doi-asserted-by":"crossref","unstructured":"Hou, I., et al.: More robots are coming: large multimodal models (ChatGPT) can solve visually diverse images of parsons problems. In: Proceedings of the 26th Australasian Computing Education Conference. (2024)","DOI":"10.1145\/3636243.3636247"},{"key":"5891_CR170","doi-asserted-by":"crossref","unstructured":"Cheng, D., et al.: Uprise: Universal prompt retrieval for improving zero-shot evaluation. arXiv preprint arXiv:2303.08518, (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.758"},{"key":"5891_CR171","doi-asserted-by":"crossref","unstructured":"Roychowdhury, S., et al.: Hallucination-minimized Data-to-answer Framework for Financial Decision-makers. In: 2023 IEEE International Conference on Big Data (BigData). IEEE. (2023)","DOI":"10.1109\/BigData59044.2023.10386232"},{"key":"5891_CR172","first-page":"9459","volume":"33","author":"P Lewis","year":"2020","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive nlp tasks. Adv. Neural. Inf. Process. Syst. 33, 9459\u20139474 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5891_CR173","unstructured":"B\u00e9chard, P., Ayala, O.M.: Reducing hallucination in structured outputs via Retrieval-Augmented Generation. arXiv preprint arXiv:2404.08189, (2024)"},{"key":"5891_CR174","unstructured":"Anantha, R., et al.: Context tuning for retrieval augmented generation. arXiv preprint arXiv:2312.05708, (2023)"},{"key":"5891_CR175","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Retrieval-augmented knowledge-intensive dialogue. In: CCF International Conference on Natural Language Processing and Chinese Computing. Springer, (2023)","DOI":"10.1007\/978-3-031-44693-1_2"},{"key":"5891_CR176","unstructured":"Saxena, S., et al.: Minimizing factual inconsistency and hallucination in large language models. arXiv preprint arXiv:2311.13878, (2023)"},{"key":"5891_CR177","doi-asserted-by":"crossref","unstructured":"Shi, W., et al.: Retrieval-augmented large language models for adolescent idiopathic scoliosis patients in shared decision-making. In: Proceedings of the 14th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics. (2023)","DOI":"10.1145\/3584371.3612956"},{"issue":"1","key":"5891_CR178","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01091-y","volume":"7","author":"S Kresevic","year":"2024","unstructured":"Kresevic, S., et al.: Optimization of hepatological clinical guidelines interpretation by large language models: a retrieval augmented generation-based framework. npj Digital Medicine 7(1), 102 (2024)","journal-title":"npj Digital Medicine"},{"key":"5891_CR179","doi-asserted-by":"publisher","DOI":"10.1016\/j.egyai.2024.100365","volume":"16","author":"V Sharma","year":"2024","unstructured":"Sharma, V., Raman, V.: A reliable knowledge processing framework for combustion science using foundation models. Energy and AI 16, 100365 (2024)","journal-title":"Energy and AI"},{"key":"5891_CR180","doi-asserted-by":"crossref","unstructured":"Wei, Z., et al.: Detecting and mitigating the ungrounded hallucinations in text generation by LLMs. In: Proceedings of the 2023 International Conference on Artificial Intelligence, Systems and Network Security. (2023)","DOI":"10.1145\/3661638.3661653"},{"key":"5891_CR181","unstructured":"Niu, C., et al.: Ragtruth: A hallucination corpus for developing trustworthy retrieval-augmented language models. arXiv preprint arXiv:2401.00396, (2023)"},{"key":"5891_CR182","unstructured":"Han, Z., et al.: Skip\\n: A simple method to reduce hallucination in large vision-language models. arXiv preprint arXiv:2402.01345, (2024)"},{"key":"5891_CR183","unstructured":"B\u00e9chard, P., Ayala, O.: Reducing hallucination in structured outputs via Retrieval-Augmented Generation. arXiv. arXiv preprint arXiv:2404.08189. (2024)"},{"key":"5891_CR184","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2025.103078","author":"Z Gu","year":"2025","unstructured":"Gu, Z., et al.: Empowering large language models for automated clinical assessment with generation-augmented retrieval and hierarchical chain-of-thought. Artif. Intell. Med. (2025). https:\/\/doi.org\/10.1016\/j.artmed.2025.103078","journal-title":"Artif. Intell. Med."},{"key":"5891_CR185","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/j.aej.2025.03.030","volume":"123","author":"T Gokcimen","year":"2025","unstructured":"Gokcimen, T., Das, B.: A novel system for strengthening security in large language models against hallucination and injection attacks with effective strategies. Alexandria Engineering Journal 123, 71\u201390 (2025)","journal-title":"Alexandria Engineering Journal"},{"key":"5891_CR186","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhang, Z., Wang, R.: Element-aware summarization with large language models: Expert-aligned evaluation and chain-of-thought method. arXiv preprint arXiv:2305.13412, (2023)","DOI":"10.18653\/v1\/2023.acl-long.482"},{"key":"5891_CR187","unstructured":"Cheng, X., et al.: Chainlm: Empowering large language models with improved chain-of-thought prompting. arXiv preprint arXiv:2403.14312, (2024)"},{"key":"5891_CR188","doi-asserted-by":"crossref","unstructured":"Huang, Q., et al.: CoQ: AN Empirical Framework for Multi-hop Question Answering Empowered by Large Language Models. In: ICASSP 2024\u20132024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, (2024)","DOI":"10.1109\/ICASSP48485.2024.10447488"},{"key":"5891_CR189","doi-asserted-by":"crossref","unstructured":"Ji, B., et al. Chain-of-thought improves text generation with citations in large language models. In: Proceedings of the AAAI Conference on Artificial Intelligence. (2024)","DOI":"10.1609\/aaai.v38i16.29794"},{"issue":"1","key":"5891_CR190","doi-asserted-by":"publisher","first-page":"11","DOI":"10.4218\/etrij.2023-0355","volume":"46","author":"J Roh","year":"2024","unstructured":"Roh, J., Kim, M., Bae, K.: Towards a small language model powered chain\u2010of\u2010reasoning for open\u2010domain question answering. ETRI Journal 46(1), 11\u201321 (2024)","journal-title":"ETRI Journal"},{"key":"5891_CR191","doi-asserted-by":"crossref","unstructured":"Li, R., Du, X.: Leveraging Structured Information for Explainable Multi-hop Question Answering and Reasoning. arXiv preprint arXiv:2311.03734, (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.452"},{"key":"5891_CR192","doi-asserted-by":"crossref","unstructured":"Saha, S., et al.: Murmur: Modular multi-step reasoning for semi-structured data-to-text generation. arXiv preprint arXiv:2212.08607, (2022)","DOI":"10.18653\/v1\/2023.findings-acl.704"},{"key":"5891_CR193","unstructured":"Iarosh, D., Panchenko, A., Salnikov, M.: On reducing factual hallucinations in graph-to-text generation using large language models. In: Proceedings of the Workshop on Generative AI and Knowledge Graphs (GenAIK). (2025)"},{"key":"5891_CR194","doi-asserted-by":"crossref","unstructured":"Das, A., et al: Enabling synergistic knowledge sharing and reasoning in large language models with collaborative multi-agents. In: 2023 IEEE 9th International Conference on Collaboration and Internet Computing (CIC). IEEE, 2023","DOI":"10.1109\/CIC58953.2023.00021"},{"key":"5891_CR195","doi-asserted-by":"crossref","unstructured":"Nathani, D., et al.: Maf: Multi-aspect feedback for improving reasoning in large language models. arXiv preprint arXiv:2310.12426, (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.407"},{"key":"5891_CR196","unstructured":"Qu, X., et al.: Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path Reasoning. arXiv preprint arXiv:2408.17150, (2024)"},{"key":"5891_CR197","unstructured":"Ranaldi, F., et al.: Prompting LLMs in Italian Language for Text-to-SQL Translation. In: CLiC-it. (2023)"},{"key":"5891_CR198","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Reflective instruction tuning: Mitigating hallucinations in large vision-language models. In: European Conference on Computer Vision. Springer, (2024)","DOI":"10.1007\/978-3-031-73113-6_12"},{"key":"5891_CR199","doi-asserted-by":"crossref","unstructured":"Zeng, Z., et al. FlowMind: Automatic Workflow Generation with LLMs. In: Proceedings of the Fourth ACM International Conference on AI in Finance. (2023)","DOI":"10.1145\/3604237.3626908"},{"key":"5891_CR200","doi-asserted-by":"crossref","unstructured":"Odede, J. Frommholz, I.: JayBot--Aiding University Students and Admission with an LLM-based Chatbot. In: Proceedings of the 2024 Conference on Human Information Interaction and Retrieval. (2024)","DOI":"10.1145\/3627508.3638293"},{"key":"5891_CR201","doi-asserted-by":"crossref","unstructured":"White, R., et al.: Clinidigest: a case study in large language model based large-scale summarization of clinical trial descriptions. In: Proceedings of the 2023 ACM Conference on Information Technology for Social Good. (2023)","DOI":"10.1145\/3582515.3609559"},{"key":"5891_CR202","doi-asserted-by":"crossref","unstructured":"Ioannidis, J., et al.: Gracenote. ai: legal generative AI for regulatory compliance. In: Proceedings of the third international workshop on artificial intelligence and intelligent assistance for legal professionals in the digital Workplace (LegalAIIA 2023). (2023)","DOI":"10.2139\/ssrn.4494272"},{"key":"5891_CR203","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1162\/tacl_a_00642","volume":"12","author":"Z He","year":"2024","unstructured":"He, Z., et al.: Exploring human-like translation strategy with large language models. Trans. Assoc. Comput. Linguist. 12, 229\u2013246 (2024)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"5891_CR204","doi-asserted-by":"crossref","unstructured":"Yong, Q., et al.: CGSMP: Controllable Generative Summarization via Multimodal Prompt. In: Proceedings of the 1st Workshop on Large Generative Models Meet Multimodal Applications. (2023)","DOI":"10.1145\/3607827.3616847"},{"key":"5891_CR205","doi-asserted-by":"crossref","unstructured":"Shim, J.-W., et al.: CPR: Mitigating large language model hallucinations with curative prompt refinement. In: 2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC). IEEE, (2024)","DOI":"10.1109\/SMC54092.2024.10830938"},{"key":"5891_CR206","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1016\/j.procs.2024.10.197","volume":"244","author":"H Shakil","year":"2024","unstructured":"Shakil, H., et al.: Utilizing GPT to enhance text summarization: a strategy to minimize hallucinations. Procedia Computer Science 244, 238\u2013247 (2024)","journal-title":"Procedia Computer Science"},{"key":"5891_CR207","doi-asserted-by":"crossref","unstructured":"Ahadian, P., Guan, Q.: A survey on hallucination in large language and foundation models. (2025)","DOI":"10.20944\/preprints202504.1236.v1"},{"key":"5891_CR208","doi-asserted-by":"crossref","unstructured":"Chen, S., et al., Propsegment: A large-scale corpus for proposition-level segmentation and entailment recognition. arXiv preprint arXiv:2212.10750, (2022)","DOI":"10.18653\/v1\/2023.findings-acl.565"},{"key":"5891_CR209","doi-asserted-by":"crossref","unstructured":"Shi, X., et al: Hallucination mitigation in natural language generation from large-scale open-domain knowledge graphs. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.770"},{"key":"5891_CR210","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Fault Diagnosis and System Maintenance Based on Large Language Models and Knowledge Graphs. In: 2023 5th International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI). IEEE, (2023)","DOI":"10.1109\/RICAI60863.2023.10489566"},{"key":"5891_CR211","unstructured":"Umapathi, L.K., Pal, A., Sankarasubbu, M.: Med-halt: Medical domain hallucination test for large language models. arXiv preprint arXiv:2307.15343, (2023)"},{"key":"5891_CR212","doi-asserted-by":"crossref","unstructured":"Ben, H., et al.: Pseudo Content Hallucination for Unpaired Image Captioning. In: Proceedings of the 2024 International Conference on Multimedia Retrieval, Association for Computing Machinery: Phuket, Thailand. p. 320\u2013329. (2024)","DOI":"10.1145\/3652583.3658080"},{"key":"5891_CR213","doi-asserted-by":"crossref","unstructured":"Jha, S.K., et al. Counterexample guided inductive synthesis using large language models and satisfiability solving. In: MILCOM 2023\u20132023 IEEE Military Communications Conference (MILCOM). IEEE, (2023)","DOI":"10.1109\/MILCOM58377.2023.10356332"},{"key":"5891_CR214","doi-asserted-by":"crossref","unstructured":"Shi, H., et al.: OPEx: A Large Language Model-Powered Framework for Embodied Instruction Following. In: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems. (2024)","DOI":"10.65109\/YYRJ6883"},{"key":"5891_CR215","doi-asserted-by":"crossref","unstructured":"Semnani, S.J., et al.: WikiChat: Stopping the hallucination of large language model chatbots by few-shot grounding on Wikipedia. arXiv preprint arXiv:2305.14292, (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.157"},{"key":"5891_CR216","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Improving the faithfulness of abstractive summarization via entity coverage control. arXiv preprint arXiv:2207.02263, (2022)","DOI":"10.18653\/v1\/2022.findings-naacl.40"},{"key":"5891_CR217","doi-asserted-by":"crossref","unstructured":"Pride, D., Cancellieri, M., Knoth, P.: CORE-GPT: Combining open access research and large language models for credible, trustworthy question answering. In: International Conference on Theory and Practice of Digital Libraries. Springer, (2023)","DOI":"10.1007\/978-3-031-43849-3_13"},{"key":"5891_CR218","doi-asserted-by":"crossref","unstructured":"Sundar, A.S., Heck, L.: cTBLS: Augmenting large language models with conversational tables. arXiv preprint arXiv:2303.12024, (2023)","DOI":"10.18653\/v1\/2023.nlp4convai-1.6"},{"key":"5891_CR219","doi-asserted-by":"crossref","unstructured":"Yang, D., et al.: RefGPT: Dialogue Generation of GPT, by GPT, and for GPT. In: Findings of the Association for Computational Linguistics: EMNLP 2023. (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.165"},{"key":"5891_CR220","unstructured":"Huo, F., et al.: Self-introspective decoding: Alleviating hallucinations for large vision-language models. arXiv preprint arXiv:2408.02032, (2024)"},{"key":"5891_CR221","doi-asserted-by":"crossref","unstructured":"Liu, L., Hulden, M.: Can a transformer pass the wug test? Tuning copying bias in neural morphological inflection models. arXiv preprint arXiv:2104.06483, (2021)","DOI":"10.18653\/v1\/2022.acl-short.84"},{"key":"5891_CR222","doi-asserted-by":"crossref","unstructured":"Huang, S., et al.: Learning Preference Model for LLMs via Automatic Preference Data Generation. In: The 2023 Conference on Empirical Methods in Natural Language Processing. (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.570"},{"key":"5891_CR223","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Data augmentation for low-resource dialogue summarization. In: Findings of the Association for Computational Linguistics: NAACL 2022. (2022)","DOI":"10.18653\/v1\/2022.findings-naacl.53"},{"key":"5891_CR224","doi-asserted-by":"crossref","unstructured":"Xiao, L., Shan, X., Chen, X.: PatternGPT: A Pattern-Driven Framework for Large Language Model Text Generation. In: Proceedings of the 2023 12th International Conference on Computing and Pattern Recognition. (2023)","DOI":"10.1145\/3633637.3633648"},{"key":"5891_CR225","doi-asserted-by":"crossref","unstructured":"Jian, Y., C. Gao, and Vosoughi, S.: Embedding Hallucination for Few-Shot Language Fine-tuning. arXiv preprint arXiv:2205.01307, (2022)","DOI":"10.18653\/v1\/2022.naacl-main.404"},{"issue":"3","key":"5891_CR226","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.13513","volume":"41","author":"C Yin","year":"2024","unstructured":"Yin, C., et al.: PowerPulse: Power energy chat model with LLaMA model fine-tuned on Chinese and power sector domain knowledge. Expert. Syst. 41(3), e13513 (2024)","journal-title":"Expert. Syst."},{"key":"5891_CR227","doi-asserted-by":"crossref","unstructured":"Liu, X. and P. Sajda. Roe: A computational-efficient anti-hallucination fine-tuning technology for large language model inspired by human learning process. in International Conference on Brain Informatics. Springer, (2023)","DOI":"10.1007\/978-3-031-43075-6_39"},{"key":"5891_CR228","doi-asserted-by":"crossref","unstructured":"Huang, W., et al.: Visual hallucinations of multi-modal large language models. arXiv preprint arXiv:2402.14683, (2024)","DOI":"10.18653\/v1\/2024.findings-acl.573"},{"key":"5891_CR229","doi-asserted-by":"crossref","unstructured":"Xiao, Y., Wang, W.Y.: On hallucination and predictive uncertainty in conditional language generation. arXiv preprint arXiv:2103.15025, (2021)","DOI":"10.18653\/v1\/2021.eacl-main.236"},{"key":"5891_CR230","doi-asserted-by":"crossref","unstructured":"Dai, Y., et al.: Exploring large language models for multi-modal out-of-distribution detection. arXiv preprint arXiv:2310.08027, (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.351"},{"key":"5891_CR231","unstructured":"Korbak, T., et al.: Controlling conditional language models without catastrophic forgetting. in International Conference on Machine Learning. PMLR. (2022)"},{"key":"5891_CR232","doi-asserted-by":"crossref","unstructured":"Yu, X., et al.: Automatic hallucination assessment for aligned large language models via transferable adversarial attacks. (2023)","DOI":"10.18653\/v1\/2024.findings-naacl.85"},{"key":"5891_CR233","doi-asserted-by":"crossref","unstructured":"Alrefaai, M. and Akg\u00fcn, D.: A Pretraining Strategy to Improve Faithfulness in Abstractive Text Summarization. In: 2023 7th International Symposium on Innovative Approaches in Smart Technologies (ISAS). IEEE, (2023)","DOI":"10.1109\/ISAS60782.2023.10391437"},{"key":"5891_CR234","doi-asserted-by":"crossref","unstructured":"Roychowdhury, S.: Journey of Hallucination-minimized Generative AI Solutions for Financial Decision Makers. In: Proceedings of the 17th ACM International Conference on Web Search and Data Mining. (2024)","DOI":"10.1145\/3616855.3635737"},{"key":"5891_CR235","unstructured":"Park, D., et al.: Mitigating dialogue hallucination for large multi-modal models via adversarial instruction tuning. arXiv preprint arXiv:2403.10492, (2024)"},{"key":"5891_CR236","unstructured":"Oh, J., et al.: ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Models. arXiv preprint arXiv:2403.05266, (2024)"},{"key":"5891_CR237","doi-asserted-by":"crossref","unstructured":"Chen, Y., Li, S., Yan, R.: FlexiQA: Leveraging LLM\u2019s Evaluation Capabilities for Flexible Knowledge Selection in Open-domain Question Answering. In: Findings of the Association for Computational Linguistics: EACL 2024. (2024)","DOI":"10.18653\/v1\/2024.findings-eacl.4"},{"key":"5891_CR238","unstructured":"Grote, A., et al.: How good are you? An empirical classification performance comparison of large language models with traditional open set recognition classifiers (short paper). In: ZEUS. (2024)"},{"key":"5891_CR239","doi-asserted-by":"crossref","unstructured":"Du, X., et al.: Evaluating large language models in class-level code generation. In: Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering. (2024)","DOI":"10.1145\/3597503.3639219"},{"key":"5891_CR240","doi-asserted-by":"crossref","unstructured":"Mihindukulasooriya, N., et al.: Text2kgbench: A benchmark for ontology-driven knowledge graph generation from text. In: International Semantic Web Conference. Springer, (2023)","DOI":"10.1007\/978-3-031-47243-5_14"},{"key":"5891_CR241","first-page":"53064","volume":"37","author":"J Oh","year":"2024","unstructured":"Oh, J., et al.: ERBench: An entity-relationship based automatically verifiable hallucination benchmark for large language models. Adv. Neural. Inf. Process. Syst. 37, 53064\u201353101 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5891_CR242","doi-asserted-by":"crossref","unstructured":"Tang, L., et al.: Tofueval: Evaluating hallucinations of llms on topic-focused dialogue summarization. arXiv preprint arXiv:2402.13249, (2024)","DOI":"10.18653\/v1\/2024.naacl-long.251"},{"key":"5891_CR243","unstructured":"Liang, X., et al.: Uhgeval: Benchmarking the hallucination of chinese large language models via unconstrained generation. arXiv preprint arXiv:2311.15296, (2023)"},{"key":"5891_CR244","doi-asserted-by":"crossref","unstructured":"Jiang, C., et al.: Hal-eval: A universal and fine-grained hallucination evaluation framework for large vision language models. In: Proceedings of the 32nd ACM International Conference on Multimedia. (2024)","DOI":"10.1145\/3664647.3680576"},{"key":"5891_CR245","doi-asserted-by":"crossref","unstructured":"Chen, K., et al.: Diahalu: A dialogue-level hallucination evaluation benchmark for large language models. arXiv preprint arXiv:2403.00896, (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.529"},{"key":"5891_CR246","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: Toolbehonest: A multi-level hallucination diagnostic benchmark for tool-augmented large language models. arXiv preprint arXiv:2406.20015, (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.637"},{"key":"5891_CR247","unstructured":"Mei, L., et al.: Not Aligned\" is Not\" Malicious\": Being Careful about Hallucinations of Large Language Models\u2019 Jailbreak. arXiv preprint arXiv:2406.11668, (2024)"},{"key":"5891_CR248","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Mm-sap: A comprehensive benchmark for assessing self-awareness of multimodal large language models in perception. arXiv preprint arXiv:2401.07529, (2024)","DOI":"10.18653\/v1\/2024.acl-long.498"},{"key":"5891_CR249","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Mementos: A comprehensive benchmark for multimodal large language model reasoning over image sequences. arXiv preprint arXiv:2401.10529, (2024)","DOI":"10.18653\/v1\/2024.acl-long.25"},{"key":"5891_CR250","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: Halueval: A large-scale hallucination evaluation benchmark for large language models. arXiv preprint arXiv:2305.11747, (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.397"},{"key":"5891_CR251","unstructured":"Wu, M., et al.: Evaluating and analyzing relationship hallucinations in large vision-language models. arXiv preprint arXiv:2406.16449, (2024)"},{"key":"5891_CR252","doi-asserted-by":"crossref","unstructured":"Cao, Q., et al.: Visdiahalbench: A visual dialogue benchmark for diagnosing hallucination in large vision-language models. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). (2024)","DOI":"10.18653\/v1\/2024.acl-long.658"},{"key":"5891_CR253","doi-asserted-by":"crossref","unstructured":"Gao, T., et al.: Enabling large language models to generate text with citations. arXiv preprint arXiv:2305.14627, (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.398"},{"key":"5891_CR254","doi-asserted-by":"crossref","unstructured":"Aharoni, R., et al.: mface: Multilingual summarization with factual consistency evaluation. arXiv preprint arXiv:2212.10622, (2022)","DOI":"10.18653\/v1\/2023.findings-acl.220"},{"key":"5891_CR255","doi-asserted-by":"crossref","unstructured":"Wang, Y.: Large Language Models Evaluate Machine Translation via Polishing. In: Proceedings of the 2023 6th International Conference on Algorithms, Computing and Artificial Intelligence. (2023)","DOI":"10.1145\/3639631.3639658"},{"key":"5891_CR256","unstructured":"Bolton, W.J., et al.: RAmBLA: A Framework for Evaluating the Reliability of LLMs as Assistants in the Biomedical Domain. arXiv preprint arXiv:2403.14578, (2024)"},{"key":"5891_CR257","doi-asserted-by":"crossref","unstructured":"Yu, X., et al.: Reeval: Automatic hallucination evaluation for retrieval-augmented large language models via transferable adversarial attacks. arXiv preprint arXiv:2310.12516, (2023)","DOI":"10.18653\/v1\/2024.findings-naacl.85"},{"key":"5891_CR258","doi-asserted-by":"crossref","unstructured":"Ramakrishna, A., et al.: Invite: a testbed of automatically generated invalid questions to evaluate large language models for hallucinations. In: Findings of the Association for Computational Linguistics: EMNLP 2023. (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.360"},{"key":"5891_CR259","unstructured":"Woo, S., et al.: RITUAL: Random Image Transformations as a Universal Anti-hallucination Lever in LVLMs. arXiv preprint arXiv:2405.17821, (2024)"},{"key":"5891_CR260","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: Halueval: A large-scale hallucination evaluation benchmark for large language models. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.397"},{"key":"5891_CR261","doi-asserted-by":"crossref","unstructured":"Kaul, P., et al.: Throne: An object-based hallucination benchmark for the free-form generations of large vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. (2024)","DOI":"10.1109\/CVPR52733.2024.02571"},{"key":"5891_CR262","doi-asserted-by":"crossref","unstructured":"Xing, S., et al.: Efuf: Efficient fine-grained unlearning framework for mitigating hallucinations in multimodal large language models. arXiv preprint arXiv:2402.09801, (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.67"},{"key":"5891_CR263","doi-asserted-by":"crossref","unstructured":"Ding, P., et al.: Hallu-pi: Evaluating hallucination in multi-modal large language models within perturbed inputs. In: Proceedings of the 32nd ACM International Conference on Multimedia. (2024)","DOI":"10.1145\/3664647.3681251"},{"key":"5891_CR264","doi-asserted-by":"crossref","unstructured":"Pezeshkpour, P.: Measuring and modifying factual knowledge in large language models. arXiv preprint arXiv:2306.06264, (2023)","DOI":"10.1109\/ICMLA58977.2023.00122"},{"key":"5891_CR265","doi-asserted-by":"crossref","unstructured":"Jing, L., et al.: Faithscore: Evaluating hallucinations in large vision-language models. arXiv preprint arXiv:2311.01477, (2023)","DOI":"10.18653\/v1\/2024.findings-emnlp.290"},{"key":"5891_CR266","doi-asserted-by":"crossref","unstructured":"Petryk, S., et al.: ALOHa: A New Measure for Hallucination in Captioning Models. arXiv preprint arXiv:2404.02904, (2024)","DOI":"10.18653\/v1\/2024.naacl-short.30"},{"key":"5891_CR267","doi-asserted-by":"crossref","unstructured":"Chun, C., et al.: CReTIHC: Designing Causal Reasoning Tasks about Temporal Interventions and Hallucinated Confoundings. In: Findings of the Association for Computational Linguistics: EMNLP 2023. (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.693"},{"key":"5891_CR268","unstructured":"Wu, Y., et al.: Ragtruth: A hallucination corpus for developing trustworthy retrieval-augmented language models. arXiv preprint arXiv:2401.00396, (2023)"},{"key":"5891_CR269","doi-asserted-by":"crossref","unstructured":"Sadat, M., et al.: Delucionqa: Detecting hallucinations in domain-specific question answering. arXiv preprint arXiv:2312.05200, (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.59"},{"key":"5891_CR270","unstructured":"Sun, Y., et al.: Benchmarking Hallucination in Large Language Models based on Unanswerable Math Word Problem. arXiv preprint arXiv:2403.03558, (2024)"},{"key":"5891_CR271","doi-asserted-by":"crossref","unstructured":"Henning, S., et al.: Is the Answer in the Text? Challenging ChatGPT with Evidence Retrieval from Instructive Text. In: The 2023 Conference on Empirical Methods in Natural Language Processing. (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.949"},{"key":"5891_CR272","unstructured":"Mubarak, H., H. Al-Khalifa, and Alkhalefah, K.S.: Halwasa: Quantify and Analyze Hallucinations in Large Language Models: Arabic as a Case Study. In: Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). (2024)"},{"key":"5891_CR273","unstructured":"Dou, C., et al.: Detection, Diagnosis, and Explanation: A Benchmark for Chinese Medial Hallucination Evaluation. In: Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). (2024)"},{"key":"5891_CR274","doi-asserted-by":"crossref","unstructured":"Luo, J., C. Xiao, and Ma, F.: Zero-resource hallucination prevention for large language models. arXiv preprint arXiv:2309.02654, (2023)","DOI":"10.18653\/v1\/2024.findings-emnlp.204"},{"key":"5891_CR275","doi-asserted-by":"crossref","unstructured":"Ahn, J., et al.: Timechara: Evaluating point-in-time character hallucination of role-playing large language models. arXiv preprint arXiv:2405.18027, (2024)","DOI":"10.18653\/v1\/2024.findings-acl.197"},{"key":"5891_CR276","doi-asserted-by":"crossref","unstructured":"Ji, Z., et al.: Anah: Analytical annotation of hallucinations in large language models. arXiv preprint arXiv:2405.20315, (2024)","DOI":"10.18653\/v1\/2024.acl-long.442"},{"key":"5891_CR277","unstructured":"Cao, Z., Y. Yang, and Zhao, H.: Autohall: Automated hallucination dataset generation for large language models. arXiv preprint arXiv:2310.00259, (2023)"},{"key":"5891_CR278","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.126712","author":"S Heo","year":"2025","unstructured":"Heo, S., Son, S., Park, H.: HaluCheck: explainable and verifiable automation for detecting hallucinations in LLM responses. Expert Syst. Appl. (2025). https:\/\/doi.org\/10.1016\/j.eswa.2025.126712","journal-title":"Expert Syst. Appl."},{"key":"5891_CR279","doi-asserted-by":"crossref","unstructured":"Yu, X., et al.: Automatic hallucination assessment for aligned large language models via transferable adversarial attacks. arXiv preprint arXiv:2310.12516, (2023)","DOI":"10.18653\/v1\/2024.findings-naacl.85"},{"key":"5891_CR280","doi-asserted-by":"crossref","unstructured":"Pu, J., et al.: Just Adjust One Prompt: Enhancing In-Context Dialogue Scoring via Constructing the Optimal Subgraph of Demonstrations and Prompts. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.590"},{"key":"5891_CR281","doi-asserted-by":"crossref","unstructured":"Norlund, T., L. Hagstr\u00f6m, and Johansson, R.: Transferring Knowledge from Vision to Language: How to Achieve it and how to Measure it? arXiv preprint arXiv:2109.11321, (2021)","DOI":"10.18653\/v1\/2021.blackboxnlp-1.10"},{"key":"5891_CR282","doi-asserted-by":"crossref","unstructured":"Gao, Y., et al.: AIGCs confuse AI too: Investigating and explaining synthetic image-induced hallucinations in large vision-language models. In: Proceedings of the 32nd ACM International Conference on Multimedia. (2024)","DOI":"10.1145\/3664647.3681467"},{"key":"5891_CR283","doi-asserted-by":"crossref","unstructured":"Malin, B., T. Kalganova, and Boulgouris, N.: A review of faithfulness metrics for hallucination assessment in Large Language Models. arXiv preprint arXiv:2501.00269, (2024)","DOI":"10.1109\/JSTSP.2025.3579203"},{"key":"5891_CR284","unstructured":"Jiang, C., et al.: On Large Language Models\u2019 Hallucination with Regard to Known Facts. arXiv preprint arXiv:2403.20009, (2024)"},{"key":"5891_CR285","unstructured":"Dhuliawala, S., et al.: Chain-of-verification reduces hallucination in large language models. arXiv preprint arXiv: 230911495. arXiv preprint arXiv: 2309.11495, (2023)"},{"key":"5891_CR286","unstructured":"Zhang, H., J. Zhang, and Wan, X.: Evaluating and Mitigating Number Hallucinations in Large Vision-Language Models: A Consistency Perspective. arXiv preprint arXiv:2403.01373, (2024)"},{"key":"5891_CR287","doi-asserted-by":"crossref","unstructured":"Sun, L., et al.: Temporal Insight Enhancement: Mitigating Temporal Hallucination in Multimodal Large Language Models. arXiv preprint arXiv:2401.09861, (2024)","DOI":"10.1007\/978-3-031-78183-4_29"},{"key":"5891_CR288","doi-asserted-by":"crossref","unstructured":"Pfeiffer, J., et al.: mmt5: Modular multilingual pre-training solves source language hallucinations. arXiv preprint arXiv:2305.14224, (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.132"},{"key":"5891_CR289","doi-asserted-by":"crossref","unstructured":"Huang, Q., et al.: CoQ:AN Empirical Framework for Multi-hop Question Answering Empowered by Large Language Models. In: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). p. 11566\u201311570. (2024)","DOI":"10.1109\/ICASSP48485.2024.10447488"},{"key":"5891_CR290","unstructured":"Park, D., et al.: Mitigating dialogue hallucination for large multi-modal models via adversarial instruction tuning. CoRR, (2024)"},{"key":"5891_CR291","doi-asserted-by":"crossref","unstructured":"Sennrich, R., J. Vamvas, and Mohammadshahi, A.: Mitigating hallucinations and off-target machine translation with source-contrastive and language-contrastive decoding. arXiv preprint arXiv:2309.07098, (2023)","DOI":"10.18653\/v1\/2024.eacl-short.4"},{"key":"5891_CR292","doi-asserted-by":"crossref","unstructured":"Boulesnane, A. and Souilah, A.: An Evolutionary Large Language Model for Hallucination Mitigation. In: 2024 1st International Conference on Electrical, Computer, Telecommunication and Energy Technologies (ECTE-Tech). IEEE, (2024)","DOI":"10.1109\/ECTE-Tech62477.2024.10851107"},{"key":"5891_CR293","doi-asserted-by":"crossref","unstructured":"Benkirane, K., et al.: Machine translation hallucination detection for low and high resource languages using large language models. arXiv preprint arXiv:2407.16470, (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.564"},{"key":"5891_CR294","doi-asserted-by":"crossref","unstructured":"Ruangchutiphophan, P., et al.: Thai Knowledge-Augmented Language Model Adaptation (ThaiKALA). In: 2023 18th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP). p. 1\u20136. (2023)","DOI":"10.1109\/iSAI-NLP60301.2023.10355001"},{"key":"5891_CR295","doi-asserted-by":"crossref","unstructured":"Zhou, S., L. Ma, and Shao, Y.: Exploring Accurate and Generic Simile Knowledge from Pre-trained Language Models. in China National Conference on Chinese Computational Linguistics. Springer, (2023)","DOI":"10.1007\/978-981-99-6207-5_22"},{"key":"5891_CR296","doi-asserted-by":"publisher","DOI":"10.1080\/0144929x.2024.2321959","author":"K Kharitonova","year":"2024","unstructured":"Kharitonova, K., et al.: Incorporating evidence into mental health Q&A: a novel method to use generative language models for validated clinical content extraction. Behaviour & Information Technology (2024). https:\/\/doi.org\/10.1080\/0144929x.2024.2321959","journal-title":"Behaviour & Information Technology"},{"key":"5891_CR297","doi-asserted-by":"crossref","unstructured":"Sarfati, N., et al.: Generating factually consistent sport highlights narrations. In: Proceedings of the 6th International Workshop on Multimedia Content Analysis in Sports. (2023)","DOI":"10.1145\/3606038.3616157"},{"key":"5891_CR298","doi-asserted-by":"crossref","unstructured":"Chen, Y.-S., et al.: SINC: Self-Supervised In-Context Learning for Vision-Language Tasks. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV). p. 15384\u201315396. (2023)","DOI":"10.1109\/ICCV51070.2023.01415"},{"key":"5891_CR299","unstructured":"Goyal, T., et al.: Training dynamics for text summarization models. arXiv preprint arXiv:2110.08370, (2021)"},{"key":"5891_CR300","doi-asserted-by":"crossref","unstructured":"Kantharaj, S., et al.: Chart-to-text: A large-scale benchmark for chart summarization. arXiv preprint arXiv:2203.06486, (2022)","DOI":"10.18653\/v1\/2022.acl-long.277"},{"key":"5891_CR301","doi-asserted-by":"crossref","unstructured":"Alambo, A., et al.: Entity-driven fact-aware abstractive summarization of biomedical literature (2022).","DOI":"10.1109\/ICPR56361.2022.9956656"},{"key":"5891_CR302","unstructured":"Li, S., et al.: OVTrack: Open-Vocabulary Multiple Object Tracking Supplemental Material."},{"key":"5891_CR303","doi-asserted-by":"publisher","first-page":"3920","DOI":"10.1109\/TIP.2022.3177318","volume":"31","author":"W Jiang","year":"2022","unstructured":"Jiang, W., et al.: Visual cluster grounding for image captioning. IEEE Trans. Image Process. 31, 3920\u20133934 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"5891_CR304","unstructured":"Alarcia, R.M.G., et al.: Bringing Systems Engineering Models to Large Language Models: An Integration of OPM with an LLM for Design Assistants. In: Proceedings of the 12th International Conference on Model-Based Software and Systems Engineering-MBSE-AI Integration. (2024)"},{"key":"5891_CR305","doi-asserted-by":"publisher","first-page":"44233","DOI":"10.1109\/ACCESS.2024.3380006","volume":"12","author":"S Rateria","year":"2024","unstructured":"Rateria, S., Singh, S.: Transparent, low resource, and context-aware information retrieval from a closed domain knowledge base. IEEE Access 12, 44233\u201344243 (2024)","journal-title":"IEEE Access"},{"key":"5891_CR306","doi-asserted-by":"crossref","unstructured":"Sekuli\u0107, I., et al.: Reliable LLM-based user simulator for task-oriented dialogue systems. arXiv preprint arXiv:2402.13374, (2024)","DOI":"10.18653\/v1\/2024.scichat-1.3"},{"key":"5891_CR307","unstructured":"Braunschweiler, N., et al.: Evaluating Large Language Models for Document-grounded Response Generation in Information-Seeking Dialogues. arXiv preprint arXiv:2309.11838, (2023)"},{"key":"5891_CR308","unstructured":"Chen, J., et al.: Benchmarking large language models in retrieval-augmented generation. arXiv. arXiv preprint arXiv:2309.01431, (2023)"},{"key":"5891_CR309","doi-asserted-by":"crossref","unstructured":"Pezeshkpour, P.: Measuring and Modifying Factual Knowledge in Large Language Models. In: 2023 International Conference on Machine Learning and Applications (ICMLA). p. 831\u2013838. (2023)","DOI":"10.1109\/ICMLA58977.2023.00122"},{"key":"5891_CR310","doi-asserted-by":"crossref","unstructured":"Wan, Y., et al.: kelly is a warm person, joseph is a role model\": Gender biases in llm-generated reference letters. arXiv preprint arXiv:2310.09219, (2023).","DOI":"10.18653\/v1\/2023.findings-emnlp.243"},{"key":"5891_CR311","doi-asserted-by":"crossref","unstructured":"Wang, G., S. Qin, and Liu, X.: Exploration and Practice of Applying Large Language Models in Home Education Guidance. In: 2023 4th International Conference on Information Science and Education (ICISE-IE). IEEE, (2023)","DOI":"10.1109\/ICISE-IE60962.2023.10456439"},{"key":"5891_CR312","doi-asserted-by":"crossref","unstructured":"Maragheh, R.Y., et al.: LLM-TAKE: Theme-Aware Keyword Extraction Using Large Language Models. In: 2023 IEEE International Conference on Big Data (BigData). p. 4318\u20134324. (2023)","DOI":"10.1109\/BigData59044.2023.10386476"},{"key":"5891_CR313","doi-asserted-by":"crossref","unstructured":"Malmi, E., et al.: Fast Text Generation with Text-Editing Models. In: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. (2023)","DOI":"10.1145\/3580305.3599579"},{"key":"5891_CR314","doi-asserted-by":"crossref","unstructured":"I, M., et al.: Mitigating Factual Inconsistency and Hallucination in Large Language Models. In: Proceedings of the 17th ACM International Conference on Web Search and Data Mining, Association for Computing Machinery: Merida, Mexico. p. 1169\u20131170. (2024)","DOI":"10.1145\/3616855.3635744"},{"key":"5891_CR315","doi-asserted-by":"crossref","unstructured":"Ngu, N., N. Lee, and Shakarian, P.: Diversity Measures: Domain-Independent Proxies for Failure in Language Model Queries. In: 2024 IEEE 18th International Conference on Semantic Computing (ICSC). p. 176\u2013182. (2024)","DOI":"10.1109\/ICSC59802.2024.00034"},{"key":"5891_CR316","unstructured":"Li, Q., et al.: Explanation regeneration via information bottleneck. arXiv preprint arXiv:2212.09603, (2022)"},{"key":"5891_CR317","doi-asserted-by":"crossref","unstructured":"Ladhak, F., et al.: When do pre-training biases propagate to downstream tasks? a case study in text summarization. In: Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics. (2023)","DOI":"10.18653\/v1\/2023.eacl-main.234"},{"key":"5891_CR318","doi-asserted-by":"crossref","unstructured":"Farina, M., et al.: Distillation of encoder-decoder transformers for sequence labelling. arXiv preprint arXiv:2302.05454, (2023)","DOI":"10.18653\/v1\/2023.findings-eacl.192"},{"key":"5891_CR319","doi-asserted-by":"crossref","unstructured":"Raman, K., et al.: Transforming sequence tagging into a seq2seq task. arXiv preprint arXiv:2203.08378, (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.813"},{"key":"5891_CR320","unstructured":"Yuan, S. and F\u00e4rber, M.: Evaluating generative models for graph-to-text generation. arXiv preprint arXiv:2307.14712, (2023)"},{"key":"5891_CR321","doi-asserted-by":"crossref","unstructured":"Gonz\u00e1lez-Corbelle, J., et al.: Dealing with hallucination and omission in neural Natural Language Generation: A use case on meteorology. In: Proceedings of the 15th International Conference on Natural Language Generation. (2022)","DOI":"10.18653\/v1\/2022.inlg-main.10"},{"key":"5891_CR322","doi-asserted-by":"crossref","unstructured":"Bax, E., et al.: Generative AI: Citations for Trust and Consensus. In: Proceedings of the Future Technologies Conference. Springer, (2023)","DOI":"10.1007\/978-3-031-47454-5_14"},{"key":"5891_CR323","doi-asserted-by":"crossref","unstructured":"Ko, D., et al.: Large language models are temporal and causal reasoners for video question answering. arXiv preprint arXiv:2310.15747, (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.261"},{"key":"5891_CR324","doi-asserted-by":"crossref","unstructured":"Wang, Y.: Large Language Models Evaluate Machine Translation via Polishing. In: 2023 6th International Conference on Algorithms, Computing and Artificial Intelligence. p. 158\u2013163. (2023)","DOI":"10.1145\/3639631.3639658"},{"key":"5891_CR325","doi-asserted-by":"crossref","unstructured":"Huo, S., N. Arabzadeh, and Clarke, C.: Retrieving Supporting Evidence for Generative Question Answering. In: Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region. p. 11\u201320. (2023)","DOI":"10.1145\/3624918.3625336"},{"key":"5891_CR326","doi-asserted-by":"crossref","unstructured":"Gilbert, H., et al.: Semantic Compression with Large Language Models. In: 2023 Tenth International Conference on Social Networks Analysis, Management and Security (SNAMS). p. 1\u20138. (2023)","DOI":"10.1109\/SNAMS60348.2023.10375400"},{"issue":"5","key":"5891_CR327","doi-asserted-by":"publisher","first-page":"1132","DOI":"10.14778\/3641204.3641221","volume":"17","author":"D Gao","year":"2024","unstructured":"Gao, D., et al.: Text-to-SQL empowered by large language models: a benchmark evaluation. Proceedings of the VLDB Endowment 17(5), 1132\u20131145 (2024)","journal-title":"Proceedings of the VLDB Endowment"},{"key":"5891_CR328","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: Data Race Detection Using Large Language Models. In: Proceedings of the SC \u201823 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis. p. 215\u2013223. (2023)","DOI":"10.1145\/3624062.3624088"},{"key":"5891_CR329","doi-asserted-by":"crossref","unstructured":"Alrefaai, M. and Akg\u00fcn, D.: A Pretraining Strategy to Improve Faithfulness in Abstractive Text Summarization. In: 2023 7th International Symposium on Innovative Approaches in Smart Technologies (ISAS). p. 1\u20134. (2023)","DOI":"10.1109\/ISAS60782.2023.10391437"},{"key":"5891_CR330","unstructured":"Gu, J.-C., et al.: Model editing can hurt general abilities of large language models. arXiv preprint arXiv:2401.04700, (2024)"},{"key":"5891_CR331","doi-asserted-by":"crossref","unstructured":"Rawte, V., et al.: The troubling emergence of hallucination in large language models--an extensive definition, quantification, and prescriptive remediations. arXiv preprint arXiv:2310.04988, (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.155"},{"key":"5891_CR332","unstructured":"Zhai, B., et al.: Halle-switch: Rethinking and controlling object existence hallucinations in large vision language models for detailed caption. arXiv preprint arXiv:2310.01779, (2023)"},{"key":"5891_CR333","doi-asserted-by":"publisher","first-page":"1500","DOI":"10.1162\/tacl_a_00615","volume":"11","author":"NM Guerreiro","year":"2023","unstructured":"Guerreiro, N.M., et al.: Hallucinations in large multilingual translation models. Trans. Assoc. Comput. Linguist. 11, 1500\u20131517 (2023)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"5891_CR334","unstructured":"Bi, B., et al.: Is factuality decoding a free lunch for llms? evaluation on knowledge editing benchmark. CoRR, (2024)"},{"key":"5891_CR335","doi-asserted-by":"crossref","unstructured":"Ahmad, M.A., I. Yaramis, and Roy, T.D.: Creating trustworthy llms: Dealing with hallucinations in healthcare ai. arXiv preprint arXiv:2311.01463, (2023)","DOI":"10.20944\/preprints202310.1662.v1"}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-025-05891-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10586-025-05891-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-025-05891-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T18:43:13Z","timestamp":1770057793000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10586-025-05891-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,2]]},"references-count":335,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["5891"],"URL":"https:\/\/doi.org\/10.1007\/s10586-025-05891-z","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"value":"1386-7857","type":"print"},{"value":"1573-7543","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,2]]},"assertion":[{"value":"19 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 October 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 December 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 February 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declaration"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not Applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics Approval"}}],"article-number":"124"}}