{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T08:08:33Z","timestamp":1761898113232,"version":"3.44.0"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031962349"},{"type":"electronic","value":"9783031962356"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-96235-6_26","type":"book-chapter","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T01:03:08Z","timestamp":1750640588000},"page":"360-373","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["LLM-Based Automated Hallucination Detection in\u00a0Multilingual Customer Service RAG Applications"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5009-0894","authenticated-orcid":false,"given":"Nikilkumar","family":"Patel","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2599-0712","authenticated-orcid":false,"given":"Haralambos","family":"Mouratidis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2874-1144","authenticated-orcid":false,"given":"Kenneth Ng Kai","family":"Zhi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,24]]},"reference":[{"key":"26_CR1","unstructured":"Claude 3.5 Sonnet (2024). https:\/\/www.anthropic.com\/claude\/sonnet"},{"key":"26_CR2","unstructured":"Arakelyan, E., et\u00a0al.: Semantic sensitivities and inconsistent predictions: measuring the fragility of NLI models (2024). https:\/\/arxiv.org\/abs\/2401.14440. _eprint: 2401.14440"},{"key":"26_CR3","unstructured":"Balesni, M., et\u00a0al.: Towards evaluations-based safety cases for AI scheming (2024). https:\/\/arxiv.org\/abs\/2411.03336"},{"key":"26_CR4","unstructured":"Bowman, S.R., et\u00a0al.: A large annotated corpus for learning natural language inference (2015). https:\/\/arxiv.org\/abs\/1508.05326. _eprint: 1508.05326"},{"key":"26_CR5","unstructured":"Bruckhaus, T.: RAG does not work for enterprises (2024). https:\/\/arxiv.org\/abs\/2406.04369"},{"key":"26_CR6","doi-asserted-by":"publisher","unstructured":"Cao, Z., et\u00a0al.: AutoHall: automated hallucination dataset generation for large language models (2023). https:\/\/doi.org\/10.48550\/arXiv.2310.00259. https:\/\/arxiv.org\/abs\/2310.00259","DOI":"10.48550\/arXiv.2310.00259"},{"key":"26_CR7","unstructured":"Chan, B.J., et\u00a0al.: Don\u2019t do RAG: when cache-augmented generation is all you need for knowledge tasks (2024). https:\/\/arxiv.org\/abs\/2412.15605"},{"key":"26_CR8","unstructured":"Chen, Y., et\u00a0al.: Hallucination detection: robustly discerning reliable answers in large language models (2024). https:\/\/arxiv.org\/abs\/2407.04121"},{"key":"26_CR9","doi-asserted-by":"publisher","unstructured":"Choudhury, M.: Generative AI has a language problem. Nature Hum. Behav. 7(11), 1802\u20131803 (2023). https:\/\/doi.org\/10.1038\/s41562-023-01716-4. https:\/\/www.nature.com\/articles\/s41562-023-01716-4","DOI":"10.1038\/s41562-023-01716-4"},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Chuang, Y.S., et\u00a0al.: Lookback lens: detecting and mitigating contextual hallucinations in large language models using only attention maps (2024). https:\/\/arxiv.org\/abs\/2407.07071v1","DOI":"10.18653\/v1\/2024.emnlp-main.84"},{"key":"26_CR11","unstructured":"Confident-AI: DeepEval\/CITATION.cff at main $$\\cdot $$ confident-AI\/DeepEval (2023). https:\/\/github.com\/confident-ai\/deepeval\/blob\/main\/CITATION.cff"},{"key":"26_CR12","doi-asserted-by":"publisher","unstructured":"Dahl, M., et\u00a0al.: Large legal fictions: profiling legal hallucinations in large language models. J. Leg. Anal. 16(1), 64\u201393 (2024). https:\/\/doi.org\/10.1093\/jla\/laae003","DOI":"10.1093\/jla\/laae003"},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"Dev, S., et\u00a0al.: On measures of biases and harms in NLP, pp. 246\u2013267. Association for Computational Linguistics (2022). https:\/\/aclanthology.org\/2022.findings-aacl.24\/","DOI":"10.18653\/v1\/2022.findings-aacl.24"},{"key":"26_CR14","doi-asserted-by":"publisher","unstructured":"Edge, D., et\u00a0al.: From local to global: a graph rag approach to query-focused summarization (2024). https:\/\/doi.org\/10.48550\/arXiv.2404.16130. https:\/\/arxiv.org\/abs\/2404.16130","DOI":"10.48550\/arXiv.2404.16130"},{"key":"26_CR15","doi-asserted-by":"publisher","unstructured":"Es, S., et\u00a0al.: RAGAS: automated evaluation of retrieval augmented generation. arXiv, Cornell University (2023). https:\/\/doi.org\/10.48550\/arxiv.2309.15217","DOI":"10.48550\/arxiv.2309.15217"},{"key":"26_CR16","unstructured":"Fan, L., et\u00a0al.: A bibliometric review of large language models research from 2017 to 2023. arXiv:2304.02020 [cs] (2023). https:\/\/arxiv.org\/abs\/2304.02020"},{"key":"26_CR17","doi-asserted-by":"publisher","unstructured":"Friel, R., et\u00a0al.: ChainPoll: a high efficacy method for LLM hallucination detection. arXiv, Cornell University (2023). https:\/\/doi.org\/10.48550\/arxiv.2310.18344","DOI":"10.48550\/arxiv.2310.18344"},{"key":"26_CR18","unstructured":"Gekhman, Z., et\u00a0al.: Does fine-tuning LLMs on new knowledge encourage hallucinations? (2024). https:\/\/arxiv.org\/abs\/2405.05904. _eprint: 2405.05904"},{"key":"26_CR19","doi-asserted-by":"publisher","unstructured":"Gemini Team, Anil, R., et\u00a0al.: Gemini: a family of highly capable multimodal models (2023). https:\/\/doi.org\/10.48550\/arXiv.2312.11805. https:\/\/arxiv.org\/abs\/2312.11805","DOI":"10.48550\/arXiv.2312.11805"},{"key":"26_CR20","unstructured":"Hu, X., et\u00a0al.: RefChecker: reference-based fine-grained hallucination checker and benchmark for large language models (2024). https:\/\/arxiv.org\/abs\/2405.14486"},{"key":"26_CR21","unstructured":"Huang, Y., Chen, S., Cai, H., Dhingra, B.: Enhancing large language models\u2019 situated faithfulness to external contexts (2024). https:\/\/arxiv.org\/abs\/2410.14675"},{"key":"26_CR22","unstructured":"Jiang, L., et\u00a0al.: Hallucination detection in LLM-enriched product listings. In: Malmasi, S., et\u00a0al. (eds.) Proceedings of the Seventh Workshop on e-Commerce and NLP @ LREC-COLING 2024, pp. 29\u201339. ELRA and ICCL, Torino, Italia, May 2024. https:\/\/aclanthology.org\/2024.ecnlp-1.4\/"},{"key":"26_CR23","unstructured":"Kayali, M., et\u00a0al.: Mind the data gap: bridging LLMs to enterprise data integration (2024). https:\/\/arxiv.org\/abs\/2412.20331"},{"key":"26_CR24","doi-asserted-by":"publisher","unstructured":"Kim, V.T., et\u00a0al.: An analysis of multilingual FActScore. In: Al-Onaizan, Y., et\u00a0al. (eds.) Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 4309\u20134333. Association for Computational Linguistics, Miami, Florida, USA, November 2024. https:\/\/doi.org\/10.18653\/v1\/2024.emnlp-main.247. https:\/\/aclanthology.org\/2024.emnlp-main.247\/","DOI":"10.18653\/v1\/2024.emnlp-main.247"},{"key":"26_CR25","unstructured":"Kossen, J., et\u00a0al.: Semantic entropy probes: robust and cheap hallucination detection in LLMs (2024). https:\/\/arxiv.org\/abs\/2406.15927"},{"key":"26_CR26","doi-asserted-by":"publisher","unstructured":"Lewis, P., et\u00a0al.: Retrieval-augmented generation for knowledge-intensive NLP tasks (2021). https:\/\/doi.org\/10.48550\/arXiv.2005.11401. https:\/\/arxiv.org\/abs\/2005.11401","DOI":"10.48550\/arXiv.2005.11401"},{"key":"26_CR27","doi-asserted-by":"publisher","unstructured":"Liu, Y., et\u00a0al.: G-Eval: NLG evaluation using GPT-4 with better human alignment (2023). https:\/\/doi.org\/10.48550\/arxiv.2303.16634","DOI":"10.48550\/arxiv.2303.16634"},{"key":"26_CR28","doi-asserted-by":"crossref","unstructured":"Manakul, P., et\u00a0al.: SelfCheckGPT: zero-resource black-box hallucination detection for generative large language models. arXiv:2303.08896 [cs] (2023). https:\/\/arxiv.org\/abs\/2303.08896","DOI":"10.18653\/v1\/2023.emnlp-main.557"},{"key":"26_CR29","unstructured":"Meinke, A., et\u00a0al.: Frontier models are capable of in-context scheming (2024). https:\/\/arxiv.org\/abs\/2412.04984"},{"key":"26_CR30","doi-asserted-by":"publisher","unstructured":"Min, S., et\u00a0al.: FActScore: fine-grained atomic evaluation of factual precision in long form text generation (2023). https:\/\/doi.org\/10.48550\/arXiv.2305.14251. https:\/\/arxiv.org\/abs\/2305.14251","DOI":"10.48550\/arXiv.2305.14251"},{"key":"26_CR31","doi-asserted-by":"publisher","unstructured":"OpenAI: GPT-4 Technical report. arXiv (Cornell University) (2023). https:\/\/doi.org\/10.48550\/arxiv.2303.08774. https:\/\/arxiv.org\/abs\/2303.08774","DOI":"10.48550\/arxiv.2303.08774"},{"key":"26_CR32","unstructured":"Pusch, L., Tim, C.: Combining LLMs and knowledge graphs to reduce hallucinations in question answering (2024). https:\/\/arxiv.org\/abs\/2409.04181"},{"key":"26_CR33","doi-asserted-by":"publisher","unstructured":"Ravi, S.S., et\u00a0al.: Lynx: an open source hallucination evaluation model (2024). https:\/\/doi.org\/10.48550\/arXiv.2407.08488. https:\/\/arxiv.org\/abs\/2407.08488","DOI":"10.48550\/arXiv.2407.08488"},{"key":"26_CR34","doi-asserted-by":"crossref","unstructured":"Rawte, V., et\u00a0al.: The troubling emergence of hallucination in large language models \u2013 an extensive definition, quantification, and prescriptive remediations (2023). https:\/\/arxiv.org\/abs\/2310.04988","DOI":"10.18653\/v1\/2023.emnlp-main.155"},{"key":"26_CR35","doi-asserted-by":"publisher","unstructured":"Esteron, S., Angela, M.: Different language usage on social media. Int. J. Adv. Eng. Manag. Sci. 7(3), 093\u2013104 (2021). https:\/\/doi.org\/10.22161\/ijaems.73.12","DOI":"10.22161\/ijaems.73.12"},{"key":"26_CR36","unstructured":"Saad-Falcon, J., et\u00a0al.: ARES: an automated evaluation framework for retrieval-augmented generation systems (2023). https:\/\/arxiv.org\/abs\/2311.09476v2"},{"key":"26_CR37","unstructured":"Sahoo, P., et\u00a0al.: A systematic survey of prompt engineering in large language models: techniques and applications. Technical report (2024). https:\/\/arxiv.org\/pdf\/2402.07927"},{"key":"26_CR38","doi-asserted-by":"crossref","unstructured":"Santy, S., Liang, J.T., Bras, R.L., Reinecke, K., Sap, M.: NLPositionality: characterizing design biases of datasets and models (2023). https:\/\/arxiv.org\/abs\/2306.01943","DOI":"10.18653\/v1\/2023.acl-long.505"},{"key":"26_CR39","doi-asserted-by":"crossref","unstructured":"Shi, W., Han, X., Lewis, M., Tsvetkov, Y., Zettlemoyer, L., Yih, S.W.T.: Trusting Your evidence: hallucinate less with context-aware decoding (2023). https:\/\/arxiv.org\/abs\/2305.14739","DOI":"10.18653\/v1\/2024.naacl-short.69"},{"key":"26_CR40","doi-asserted-by":"crossref","unstructured":"Shuster, K., Poff, S., Chen, M., Kiela, D., Weston, J.: Retrieval augmentation reduces hallucination in conversation. arXiv:2104.07567 [cs] (2021). https:\/\/arxiv.org\/abs\/2104.07567","DOI":"10.18653\/v1\/2021.findings-emnlp.320"},{"key":"26_CR41","unstructured":"Llama Team, AI Meta: The Llama 3 herd of models. Technical report (2024). https:\/\/arxiv.org\/pdf\/2407.21783"},{"key":"26_CR42","unstructured":"Tonmoy, S., et\u00a0al.: A comprehensive survey of hallucination mitigation techniques in large language models (2024). https:\/\/arxiv.org\/abs\/2401.01313"},{"key":"26_CR43","unstructured":"Vishwanath, P.R., et\u00a0al.: Faithfulness hallucination detection in healthcare AI. In: Artificial Intelligence and Data Science for Healthcare: Bridging Data-Centric AI and People-Centric Healthcare (2024). https:\/\/openreview.net\/forum?id=6eMIzKFOpJ"},{"key":"26_CR44","unstructured":"Wang, Y.H., et\u00a0al.: CLUE: concept-level uncertainty estimation for large language models (2024). https:\/\/arxiv.org\/abs\/2409.03021"},{"key":"26_CR45","unstructured":"Wu, K., Wu, E., Zou, J.: ClashEval: quantifying the tug-of-war between an LLM\u2019s internal prior and external evidence (2024). https:\/\/arxiv.org\/abs\/2404.10198"},{"key":"26_CR46","doi-asserted-by":"publisher","unstructured":"Yao, S., et\u00a0al.: ReAct: synergizing reasoning and acting in language models (2023). https:\/\/doi.org\/10.48550\/arXiv.2210.03629. https:\/\/arxiv.org\/abs\/2210.03629","DOI":"10.48550\/arXiv.2210.03629"},{"key":"26_CR47","doi-asserted-by":"publisher","unstructured":"Yu, H., et\u00a0al.: Evaluation of retrieval-augmented generation: a survey (2024). https:\/\/doi.org\/10.48550\/arXiv.2405.07437. https:\/\/arxiv.org\/abs\/2405.07437","DOI":"10.48550\/arXiv.2405.07437"},{"key":"26_CR48","unstructured":"Zhang, J., Li, Z., Das, K., Malin, B.A., Kumar, S.: SAC3: reliable hallucination detection in black-box language models via semantic-aware cross-check consistency (2023). https:\/\/arxiv.org\/abs\/2311.01740"},{"key":"26_CR49","unstructured":"Zhao, W., et\u00a0al.: WildHallucinations: evaluating long-form factuality in LLMs with real-world entity queries (2024). https:\/\/arxiv.org\/abs\/2407.17468. _eprint: 2407.17468"},{"key":"26_CR50","doi-asserted-by":"crossref","unstructured":"Zhuo, J., et\u00a0al.: ProSA: assessing and understanding the prompt sensitivity of LLMs (2024). https:\/\/arxiv.org\/abs\/2410.12405","DOI":"10.18653\/v1\/2024.findings-emnlp.108"}],"container-title":["IFIP Advances in Information and Communication Technology","Artificial Intelligence Applications and Innovations"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-96235-6_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T13:21:42Z","timestamp":1757942502000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-96235-6_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031962349","9783031962356"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-96235-6_26","relation":{},"ISSN":["1868-4238","1868-422X"],"issn-type":[{"type":"print","value":"1868-4238"},{"type":"electronic","value":"1868-422X"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"24 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AIAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IFIP International Conference on Artificial Intelligence Applications and Innovations","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Limassol","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cyprus","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aiai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ifipaiai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}