{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T01:00:43Z","timestamp":1781226043998,"version":"3.54.1"},"reference-count":54,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100013091","name":"Science and Technology Major Project of Guangxi","doi-asserted-by":"publisher","award":["AA23062031"],"award-info":[{"award-number":["AA23062031"]}],"id":[{"id":"10.13039\/501100013091","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52275079"],"award-info":[{"award-number":["52275079"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.knosys.2026.115962","type":"journal-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T23:28:36Z","timestamp":1775604516000},"page":"115962","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Counterfactual Residual Contrastive Learning for mitigating sycophancy in Large Vision Language Models"],"prefix":"10.1016","volume":"343","author":[{"given":"Yaru","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8739-4740","authenticated-orcid":false,"given":"Yanxue","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinming","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianbo","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.115962_b1","series-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"10.1016\/j.knosys.2026.115962_b2","series-title":"Qwen3 technical report","author":"Yang","year":"2025"},{"key":"10.1016\/j.knosys.2026.115962_b3","series-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024"},{"key":"10.1016\/j.knosys.2026.115962_b4","series-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"10.1016\/j.knosys.2026.115962_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.114689","article-title":"A comprehensive review of llm-based content moderation: Advancements, challenges, and future directions","author":"Chen","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.115962_b6","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Lu","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.115962_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.114307","article-title":"Llm-powered explanations: Unraveling recommendations through subgraph reasoning","author":"Shi","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.115962_b8","article-title":"TempQA: An LLM-based framework for temporal knowledge graph question answering","author":"Hu","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.115962_b9","doi-asserted-by":"crossref","unstructured":"M.J. Lee, D. Gong, M. Cho, Video Summarization with Large Language Models, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 18981\u201318991.","DOI":"10.1109\/CVPR52734.2025.01768"},{"key":"10.1016\/j.knosys.2026.115962_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.114094","article-title":"Leveraging temporal validity of rules via LLMs for enhanced temporal knowledge graph reasoning","author":"Pan","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.115962_b11","series-title":"Hallucination of multimodal large language models: A survey","author":"Bai","year":"2024"},{"issue":"2","key":"10.1016\/j.knosys.2026.115962_b12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3703155","article-title":"A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions","volume":"43","author":"Huang","year":"2025","journal-title":"ACM Trans. Inf. Syst."},{"key":"10.1016\/j.knosys.2026.115962_b13","doi-asserted-by":"crossref","unstructured":"T. Guan, F. Liu, X. Wu, R. Xian, Z. Li, X. Liu, X. Wang, L. Chen, F. Huang, Y. Yacoob, 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, pp. 14375\u201314385.","DOI":"10.1109\/CVPR52733.2024.01363"},{"key":"10.1016\/j.knosys.2026.115962_b14","doi-asserted-by":"crossref","unstructured":"Y. Wu, L. Zhang, H. Yao, J. Du, K. Yan, S. Ding, Y. Wu, X. Li, Antidote: A Unified Framework for Mitigating LVLM Hallucinations in Counterfactual Presupposition and Object Perception, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 14646\u201314656.","DOI":"10.1109\/CVPR52734.2025.01365"},{"key":"10.1016\/j.knosys.2026.115962_b15","doi-asserted-by":"crossref","DOI":"10.1016\/j.neubiorev.2025.106351","article-title":"Links between auditory verbal hallucinations and auditory emotional perception: a systematic review","author":"Amorim","year":"2025","journal-title":"Neurosci. Biobehav. Rev."},{"key":"10.1016\/j.knosys.2026.115962_b16","doi-asserted-by":"crossref","unstructured":"T.-H. Wu, G. Biamby, D. Chan, L. Dunlap, R. Gupta, X. Wang, J.E. Gonzalez, T. Darrell, See say and segment: Teaching lmms to overcome false premises, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 13459\u201313469.","DOI":"10.1109\/CVPR52733.2024.01278"},{"key":"10.1016\/j.knosys.2026.115962_b17","doi-asserted-by":"crossref","unstructured":"Y. Liu, Z. Liang, Y. Wang, X. Wu, F. Tang, M. He, J. Li, Z. Liu, H. Yang, S. Lim, et al., Unveiling the Ignorance of MLLMs: Seeing Clearly, Answering Incorrectly, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 9087\u20139097.","DOI":"10.1109\/CVPR52734.2025.00849"},{"key":"10.1016\/j.knosys.2026.115962_b18","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"25543","article-title":"Detecting and mitigating hallucination in large vision language models via fine-grained ai feedback","volume":"vol. 39","author":"Xiao","year":"2025"},{"key":"10.1016\/j.knosys.2026.115962_b19","series-title":"Mitigating hallucination in large multi-modal models via robust instruction tuning","author":"Liu","year":"2023"},{"key":"10.1016\/j.knosys.2026.115962_b20","doi-asserted-by":"crossref","unstructured":"C. Jiang, H. Xu, M. Dong, J. Chen, W. Ye, M. Yan, Q. Ye, J. Zhang, F. Huang, S. Zhang, Hallucination augmented contrastive learning for multimodal large language model, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 27036\u201327046.","DOI":"10.1109\/CVPR52733.2024.02553"},{"key":"10.1016\/j.knosys.2026.115962_b21","series-title":"Visual multi-agent system: Mitigating hallucination snowballing via visual flow","author":"Yu","year":"2025"},{"key":"10.1016\/j.knosys.2026.115962_b22","series-title":"How language model hallucinations can snowball","author":"Zhang","year":"2023"},{"key":"10.1016\/j.knosys.2026.115962_b23","unstructured":"T. Yang, Z. Li, J. Cao, C. Xu, Understanding and mitigating hallucination in large vision-language models via modular attribution and intervention, in: The Thirteenth International Conference on Learning Representations."},{"key":"10.1016\/j.knosys.2026.115962_b24","doi-asserted-by":"crossref","unstructured":"H. Yin, G. Si, Z. Wang, ClearSight: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large Language Models, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 14625\u201314634.","DOI":"10.1109\/CVPR52734.2025.01363"},{"key":"10.1016\/j.knosys.2026.115962_b25","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.114470","article-title":"MRBalance: A framework for enhancing event causality identification in multi-agent debates via role assignment","author":"Zou","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.115962_b26","series-title":"Attention reallocation: Towards zero-cost and controllable hallucination mitigation of mllms","author":"Tu","year":"2025"},{"key":"10.1016\/j.knosys.2026.115962_b27","series-title":"MLLMs are deeply affected by modality bias","author":"Zheng","year":"2025"},{"key":"10.1016\/j.knosys.2026.115962_b28","series-title":"Lanp: Rethinking the impact of language priors in large vision-language models","author":"Wu","year":"2025"},{"key":"10.1016\/j.knosys.2026.115962_b29","article-title":"P-MLP: Language-conditioned task planning with multimodal lexical priors over labels","author":"Liu","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.115962_b30","doi-asserted-by":"crossref","first-page":"1032","DOI":"10.1162\/TACL.a.18","article-title":"Muri: High-quality instruction tuning datasets for low-resource languages via reverse instructions","volume":"13","author":"K\u00f6ksal","year":"2025","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10.1016\/j.knosys.2026.115962_b31","doi-asserted-by":"crossref","first-page":"771","DOI":"10.1162\/tacl_a_00673","article-title":"Instructed to bias: Instruction-tuned language models exhibit emergent cognitive bias","volume":"12","author":"Itzhak","year":"2024","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10.1016\/j.knosys.2026.115962_b32","doi-asserted-by":"crossref","unstructured":"J. Lin, H. Chen, Y. Fan, Y. Fan, X. Jin, H. Su, J. Fu, X. Shen, Multi-Layer Visual Feature Fusion in Multimodal LLMs: Methods, Analysis, and Best Practices, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 4156\u20134166.","DOI":"10.1109\/CVPR52734.2025.00393"},{"key":"10.1016\/j.knosys.2026.115962_b33","series-title":"Rethinking visual layer selection in multimodal LLMs","author":"Chen","year":"2025"},{"key":"10.1016\/j.knosys.2026.115962_b34","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.114240","article-title":"Tapas: enabling faithful data-to-text generation through task-adaptive pre-training with data alignment strategy","author":"Sun","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.115962_b35","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.114426","article-title":"Provide explainable clues: A generative traceable method for knowledge graph completion","author":"Ma","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.115962_b36","series-title":"Hallusionbench: You see what you think? or you think what you see? an image-context reasoning benchmark challenging for gpt-4v (ision), llava-1.5, and other multi-modality models","first-page":"12","author":"Liu","year":"2023"},{"key":"10.1016\/j.knosys.2026.115962_b37","doi-asserted-by":"crossref","unstructured":"T. Liu, Y. Zhang, C. Brockett, Y. Mao, Z. Sui, W. Chen, W.B. Dolan, A token-level reference-free hallucination detection benchmark for free-form text generation, in: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022, pp. 6723\u20136737.","DOI":"10.18653\/v1\/2022.acl-long.464"},{"key":"10.1016\/j.knosys.2026.115962_b38","series-title":"Evaluating object hallucination in large vision-language models","author":"Li","year":"2023"},{"key":"10.1016\/j.knosys.2026.115962_b39","doi-asserted-by":"crossref","unstructured":"S. Leng, H. Zhang, G. Chen, X. Li, S. Lu, C. Miao, L. Bing, 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, pp. 13872\u201313882.","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"10.1016\/j.knosys.2026.115962_b40","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"18135","article-title":"Detecting and preventing hallucinations in large vision language models","volume":"vol. 38","author":"Gunjal","year":"2024"},{"key":"10.1016\/j.knosys.2026.115962_b41","doi-asserted-by":"crossref","unstructured":"Q. Huang, X. Dong, P. Zhang, B. Wang, C. He, J. Wang, D. Lin, W. Zhang, N. Yu, 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, pp. 13418\u201313427.","DOI":"10.1109\/CVPR52733.2024.01274"},{"issue":"12","key":"10.1016\/j.knosys.2026.115962_b42","doi-asserted-by":"crossref","DOI":"10.1007\/s11432-024-4251-x","article-title":"Woodpecker: Hallucination correction for multimodal large language models","volume":"67","author":"Yin","year":"2024","journal-title":"Sci. China Inf. Sci."},{"key":"10.1016\/j.knosys.2026.115962_b43","series-title":"Analyzing and mitigating object hallucination in large vision-language models","author":"Zhou","year":"2023"},{"key":"10.1016\/j.knosys.2026.115962_b44","series-title":"Halc: Object hallucination reduction via adaptive focal-contrast decoding","author":"Chen","year":"2024"},{"key":"10.1016\/j.knosys.2026.115962_b45","series-title":"Adaptive contrastive decoding in retrieval-augmented generation for handling noisy contexts","author":"Kim","year":"2024"},{"key":"10.1016\/j.knosys.2026.115962_b46","series-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023"},{"key":"10.1016\/j.knosys.2026.115962_b47","series-title":"Llavanext: Improved reasoning, ocr, and world knowledge","author":"Liu","year":"2024"},{"key":"10.1016\/j.knosys.2026.115962_b48","series-title":"Rlaif-v: Aligning mllms through open-source ai feedback for super gpt-4v trustworthiness","first-page":"arXiv","author":"Yu","year":"2024"},{"key":"10.1016\/j.knosys.2026.115962_b49","doi-asserted-by":"crossref","unstructured":"S. Lee, S.H. Park, Y. Jo, M. Seo, Volcano: mitigating multimodal hallucination through self-feedback guided revision, in: Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 2024, pp. 391\u2013404.","DOI":"10.18653\/v1\/2024.naacl-long.23"},{"key":"10.1016\/j.knosys.2026.115962_b50","series-title":"Multimodal chain-of-thought reasoning: A comprehensive survey","author":"Wang","year":"2025"},{"key":"10.1016\/j.knosys.2026.115962_b51","doi-asserted-by":"crossref","unstructured":"J. Liu, Y. Fu, R. Xie, R. Xie, X. Sun, F. Lian, Z. Kang, X. Li, PhD: A ChatGPT-Prompted Visual Hallucination Evaluation Dataset, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 19857\u201319866.","DOI":"10.1109\/CVPR52734.2025.01849"},{"key":"10.1016\/j.knosys.2026.115962_b52","unstructured":"N. Muennighoff, Q. Liu, A. Zebaze, Q. Zheng, B. Hui, T.Y. Zhuo, S. Singh, X. Tang, L. Von Werra, S. Longpre, Octopack: Instruction tuning code large language models, in: NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following, 2023."},{"key":"10.1016\/j.knosys.2026.115962_b53","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102706","article-title":"Prompt-guided image color aesthetics assessment: Models, datasets and benchmarks","volume":"114","author":"He","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.knosys.2026.115962_b54","series-title":"GKG-LLM: A unified framework for generalized knowledge graph construction","author":"Zhang","year":"2025"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095070512600688X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095070512600688X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T00:17:44Z","timestamp":1781223464000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S095070512600688X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":54,"alternative-id":["S095070512600688X"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.115962","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Counterfactual Residual Contrastive Learning for mitigating sycophancy in Large Vision Language Models","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.115962","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"115962"}}