Elamur Research⌕
☰
home / papers / 2026 / Vision-Language Introspection: Mitigating Overconfident Hallucinations in MLLMs via Interpretable Bi-Causal Steering

Vision-Language Introspection: Mitigating Overconfident Hallucinations in MLLMs via Interpretable Bi-Causal Steering

Paper · 2026 · Shuliang Liu, Songbo Yang, Dong Fang et al.

Summary

Multimodal LLMs often describe objects that are not in the image. The authors trace this to models trusting language-based expectations over what the image actually shows. They propose Vision-Language Introspection (VLI), a training-free method applied at inference time.

VLI runs the model twice for each token: once with the image and once with the visual input masked. When the two output distributions disagree strongly, measured by Jensen-Shannon divergence, VLI picks the token driving the conflict. It then uses pre-selected "expert" attention heads to locate the image region supporting that token.

Next, it builds two counterfactual inputs by inpainting: one keeps only that region (Anchor-Only), the other keeps only the background (Context-Only). The difference between their hidden states yields an instance-specific steering vector, applied across layers. An adaptive calibration step then lowers confidence that the image does not support.

Tested on LLaVA-1.5 and Qwen3-VL, VLI reduces hallucinations on MMHal-Bench and raises POPE accuracy. This matters because it moves interpretability from diagnosis to active correction without retraining.

Key points

  • Reported gains over the base model:
    • MMHal-Bench hallucination rate drops by up to 12.67%.
    • POPE accuracy rises by 5.8% according to the abstract, and by up to 6.33% according to the introduction.
    • Margins over prior state-of-the-art methods are 5.37% (MMHal) and 1.60% (POPE).
  • Expert-head selection: reliable heads are chosen offline on a validation set, by measuring how much attention falls inside ground-truth object regions. This step is inspired by SEVI.
  • Best hyperparameters:
    • anchor energy ratio ρ = 0.4 (LLaVA-1.5: score 3.11, hallucination rate 45.63%);
    • risk threshold θ = 0.10;
    • steering strength α = 0.5 (Qwen3-VL score up to 4.32).
    • Values of α ≥ 0.7 hurt results; at α = 0.9, LLaVA's hallucination rate reaches 52.65%.
  • Layer-wise analysis: removing the anchor region changes hidden states far more than removing the background, and this gap grows with depth. The authors read this as evidence that background context drives the base model's hallucinations.
  • Limitations: counterfactual passes add computation and GPU memory. The method also depends on the base model having attention heads that localize objects well, which may fail for abstract concepts.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Hong Kong University of Science and TechnologyHong Kong · China142 works · 25,136 citations🎓The Hong Kong University of Science and Technology (Guangzhou)Guangzhou · China53 works · 1,367 citations

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksComputer Vision and Pattern Recognition · 2,869 works

🧭 Topics 1Research subjects and languages the work is about.Vision & language · 657 works

Cite

Cite as Shuliang Liu, Songbo Yang, Dong Fang, Sihang Jia, Yuqi Tang, Lingfeng Su, Ruoshui Peng, Yibo Yan, Xin Zou and Xuming Hu. 2026. Vision-Language Introspection: Mitigating Overconfident Hallucinations in MLLMs via Interpretable Bi-Causal Steering. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-long.1784

@inproceedings{liu2026vision,
  title = {{Vision-Language Introspection: Mitigating Overconfident Hallucinations in MLLMs via Interpretable Bi-Causal Steering}},
  author = {Shuliang Liu, Songbo Yang, Dong Fang, Sihang Jia, Yuqi Tang, Lingfeng Su, Ruoshui Peng, Yibo Yan, Xin Zou and Xuming Hu},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.1784},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1784}
}

References

70 references, 9 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Wenbin An, Feng Tian, Sicong Leng, Jiahao Nie, Haonan Lin, QianYing Wang, Ping Chen, Xiaoqin Zhang, and Shijian Lu. 2025. Mitigating object hallucinations in large vision-language models with assembly of global and local attention. In Proceedings of the Computer Vision and Pattern Recognition Confer… find
  2. Kyungho Bae, Jinhyung Kim, Sihaeng Lee, Soony-oung Lee, Gunhee Lee, and Jinwoo Choi. 2025. Mash-vlm: Mitigating action-scene hallucination in video-llms through disentangled spatial-temporal representations. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 13744– 13753… find
  3. Shuai Bai, Yuxuan Cai, Ruizhe Chen, Keqin Chen, Xionghui Chen, Zesen Cheng, Lianghao Deng, Wei Ding, Chang Gao, Chunjiang Ge, Wenbin Ge, Zhifang Guo, Qidong Huang, Jie Huang, Fei Huang, Binyuan Hui, Shutong Jiang, Zhaohai Li, Mingsheng Li, Mei Li, Kaixin Li, Zicheng Lin, Junyang Lin, Xuejing Liu, Ji… — Qwen3-VL Technical Report
  4. Boxu Chen, Ziwei Zheng, Le Yang, Zeyu Geng, Zhengyu Zhao, Chenhao Lin, and Chao Shen. 2025a. find
  5. Seeing it or not? interpretable vision-aware latent steering to mitigate object hallucinations. arXiv preprint arXiv:2505.17812. — [arXiv:2505.17812](https://arxiv.org/abs/2505.17812) find
  6. Guoqing Chen, Fu Zhang, Jinghao Lin, Chenglong Lu, and Jingwei Cheng. 2025b. 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, pages 6798–6815.
  7. Jiahe Chen, Jiaying He, Qian Shao, Qiyuan Chen, Jiahe Ying, Hongxia Xu, Jintai Chen, Jianwei Zheng, and Jian Wu. 2025c. Mitigating hallucination of large vision-language models via dynamic logits calibration. arXiv preprint arXiv:2506.21509. — [arXiv:2506.21509](https://arxiv.org/abs/2506.21509) find
  8. Wei Chen, Xin Yan, Bin Wen, Fan Yang, Tingting Gao, Di Zhang, and Long Chen. 2025d. Decoupling contrastive decoding: Robust hallucination mitigation in multimodal large language models. arXiv preprint arXiv:2504.08809. — [arXiv:2504.08809](https://arxiv.org/abs/2504.08809) find
  9. Xinlong Chen, Yuanxing Zhang, Qiang Liu, Junfei Wu, Fuzheng Zhang, and Tieniu Tan. 2025e. Mixture of decoding: An attention-inspired adaptive decoding strategy to mitigate hallucinations in large vision-language models. arXiv preprint arXiv:2505.17061. find
  10. Zhaorun Chen, Zhuokai Zhao, Hongyin Luo, Huaxiu Yao, Bo Li, and Jiawei Zhou. 2024. Halc: Object hallucination reduction via adaptive focal-contrast decoding. arXiv preprint arXiv:2403.00425. — [arXiv:2403.00425](https://arxiv.org/abs/2403.00425) find
  11. Jingyuan Deng and Yujiu Yang. 2025. Maskcd: Mitigating lvlm hallucinations by image head masked contrastive decoding. arXiv preprint arXiv:2510.02790. find
  12. Xinpeng Ding, Kui Zhang, Jianhua Han, Lanqing Hong, Hang Xu, and Xiaomeng Li. 2025. Pami-vdpo: Mitigating video hallucinations by prompt-aware multi-instance video preference learning. arXiv preprint arXiv:2504.05810. — [arXiv:2504.05810](https://arxiv.org/abs/2504.05810) find
  13. Jinhao Duan, Fei Kong, Hao Cheng, James Diffenderfer, Bhavya Kailkhura, Lichao Sun, Xiaofeng Zhu, Xiaoshuang Shi, and Kaidi Xu. 2025. Truth-print: Mitigating lvlm object hallucination via latent truthful-guided pre-intervention. arXiv preprint arXiv:2503.10602. — [arXiv:2503.10602](https://arxiv.org/abs/2503.10602) find
  14. Alessandro Favero, Luca Zancato, Matthew Trager, Siddharth Choudhary, Pramuditha Perera, Alessandro Achille, Ashwin Swaminathan, and Stefano Soatto. 2024. Multi-modal hallucination control by visual information grounding. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recog… find
  15. Yuhan Fu, Ruobing Xie, Xingwu Sun, Zhanhui Kang, and Xirong Li. 2025. Mitigating hallucination in multimodal large language model via hallucination-targeted direct preference optimization. In Findings of the Association for Computational Linguistics: ACL 2025, pages 16563–16577. find
  16. Jinghan He, Kuan Zhu, Haiyun Guo, Junfeng Fang, Zhenglin Hua, Yuheng Jia, Ming Tang, Tat-Seng Chua, and Jinqiao Wang. 2025. Cracking the code of hallucination in lvlms with vision-aware head divergence. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volum…
  17. Yonghua Hei, Yibo Yan, Shuliang Liu, Huiyu Zhou, Linfeng Zhang, and Xuming Hu. 2025. Unlocking speech instruction data potential with query rewriting. arXiv preprint arXiv:2507.08603. find
  18. Alice Heiman, Xiaoman Zhang, Emma Chen, Sung Eun Kim, and Pranav Rajpurkar. 2025. Factchexcker: Mitigating measurement hallucinations in chest x-ray report generation models. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 30787–30796. find
  19. Xuming Hu, Shuliang Liu, Chenwei Zhang, Shuang Li, Lijie Wen, and Philip S Yu. 2022. Hiure: Hierarchical exemplar contrastive learning for unsupervised relation extraction. arXiv preprint arXiv:2205.02225. find
  20. Qidong Huang, Xiaoyi Dong, Pan Zhang, Bin Wang, Conghui He, Jiaqi Wang, Dahua Lin, Weiming Zhang, and Nenghai Yu. 2024. 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 Vis… find
  21. Yu Huang, Junhao Chen, Shuliang Liu, Hanqian Li, Qi Zheng, Xuming Hu, et al. 2025. Video signature: In-generation watermarking for latent video diffusion models. arXiv preprint arXiv:2506.00652. — [arXiv:2506.00652](https://arxiv.org/abs/2506.00652) find
  22. Jiahao Huo, Shuliang Liu, Bin Wang, Junyan Zhang, Yibo Yan, Aiwei Liu, Xuming Hu, and Mingxun Zhou. 2025. Pmark: Towards robust and distortion-free semantic-level watermarking with channel constraints. arXiv preprint arXiv:2509.21057. — [arXiv:2509.21057](https://arxiv.org/abs/2509.21057) find
  23. Chaoya Jiang, Haiyang Xu, Mengfan Dong, Jiaxing Chen, Wei Ye, Ming Yan, Qinghao Ye, Ji Zhang, Fei Huang, and Shikun Zhang. 2024. Hallucination augmented contrastive learning for multimodal large language model. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pag… find
  24. Zhangqi Jiang, Junkai Chen, Beier Zhu, Tingjin Luo, Yankun Shen, and Xu Yang. 2025. Devils in middle layers of large vision-language models: Interpreting, detecting and mitigating object hallucinations via attention lens. In Proceedings of the Computer Vision and Pattern Recognition Conference, page… find
  25. Adam Tauman Kalai, Ofir Nachum, Santosh S Vempala, and Edwin Zhang. 2025. Why language models hallucinate. arXiv preprint arXiv:2509.04664. — [arXiv:2509.04664](https://arxiv.org/abs/2509.04664) find
  26. Seil Kang, Jinyeong Kim, Junhyeok Kim, and Seong Jae Hwang. 2025. See what you are told: Visual attention sink in large multimodal models. arXiv preprint arXiv:2503.03321. — [arXiv:2503.03321](https://arxiv.org/abs/2503.03321) find
  27. Prannay Kaul, Zhizhong Li, Hao Yang, Yonatan Dukler, Ashwin Swaminathan, CJ Taylor, and Stefano Soatto. 2024. 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 Recogn… find
  28. Jihoon Lee and Min Song. 2025. Retrieval visual contrastive decoding to mitigate object hallucinations in large vision-language models. arXiv preprint arXiv:2505.20569. find
  29. Sicong Leng, Hang Zhang, Guanzheng Chen, Xin Li, Shijian Lu, Chunyan Miao, and Lidong Bing. 2024. 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, pages 13872–13…
  30. Wei Li, Zhen Huang, Houqiang Li, Le Lu, Yang Lu, Xinmei Tian, Xu Shen, and Jieping Ye. 2025a. Visual evidence prompting mitigates hallucinations in large vision-language models. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages… find
  31. Yifan Li, Yifan Du, Kun Zhou, Jinpeng Wang, Xin Zhao, and Ji-Rong Wen. 2023. Evaluating object hallucination in large vision-language models. In The 2023 Conference on Empirical Methods in Natural Language Processing.
  32. Zhuowei Li, Haizhou Shi, Yunhe Gao, Di Liu, Zhenting Wang, Yuxiao Chen, Ting Liu, Long Zhao, Hao Wang, and Dimitris N Metaxas. 2025b. The hidden life of tokens: Reducing hallucination of large vision-language models via visual information steering. arXiv preprint arXiv:2502.03628. — [arXiv:2502.03628](https://arxiv.org/abs/2502.03628) find
  33. Zipeng Ling, Yuehao Tang, Shuliang Liu, Junqi Yang, Shenghong Fu, Chen Huang, Kejia Huang, Yao Wan, Zhichao Hou, and Xuming Hu. 2025. Wak-enllm: Evaluating reasoning potential and stability in llms via fine-grained benchmarking. arXiv preprint arXiv:2507.16199. — [arXiv:2507.16199](https://arxiv.org/abs/2507.16199) find
  34. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. Advances in neural information processing systems, 36:34892– 34916.
  35. Jiazhen Liu, Yuhan Fu, Ruobing Xie, Runquan Xie, Xingwu Sun, Fengzong Lian, Zhanhui Kang, and Xirong Li. 2024a. Phd: A chatgpt-prompted visual hallucination evaluation dataset. arXiv preprint arXiv:2403.11116. — [arXiv:2403.11116](https://arxiv.org/abs/2403.11116) find
  36. Sheng Liu, Haotian Ye, and James Zou. 2025a. Reducing hallucinations in large vision-language models via latent space steering. In The Thirteenth International Conference on Learning Representations. find
  37. Shi Liu, Kecheng Zheng, and Wei Chen. 2024b. Paying more attention to image: A training-free method for alleviating hallucination in lvlms. In European Conference on Computer Vision, pages 125–140. Springer. find
  38. Shuliang Liu, Xingyu Li, Hongyi Liu, Dong Fang, Yibo Yan, Bingchen Duan, Qi Zheng, Lingfeng Su, and Xuming Hu. 2026. Distilling the thought, watermarking the answer: A principle semantic guided watermark for large reasoning models. arXiv preprint arXiv:2601.05144. find
  39. Shuliang Liu, Hongyi Liu, Aiwei Liu, Bingchen Duan, Qi Zheng, Yibo Yan, He Geng, Peijie Jiang, Jia Liu, and Xuming Hu. 2025b. A survey on proactive defense strategies against misinformation in large language models. arXiv preprint arXiv:2507.05288. find
  40. Shuliang Liu, Qi Zheng, Jesse Jiaxi Xu, Yibo Yan, He Geng, Aiwei Liu, Peijie Jiang, Jia Liu, Yik-Cheung Tam, and Xuming Hu. 2025c. Vla-mark: A cross modal watermark for large vision-language alignment model. arXiv preprint arXiv:2507.14067. — [arXiv:2507.14067](https://arxiv.org/abs/2507.14067) find
  41. Xinyu Lyu, Beitao Chen, Lianli Gao, Hengtao Shen, and Jingkuan Song. 2024. Alleviating hallucinations in large vision-language models through hallucination-induced optimization. Advances in Neural Information Processing Systems, 37:122811–122832. find
  42. Kyungmin Min, Minbeom Kim, Kang-il Lee, Dongryeol Lee, and Kyomin Jung. 2024. Mitigating hallucinations in large vision-language models via summary-guided decoding. arXiv preprint arXiv:2410.13321. find
  43. Eunkyu Park, Minyeong Kim, and Gunhee Kim. 2025. Halloc: Token-level localization of hallucinations for vision language models. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 29893–29903. find
  44. Baochang Ren, Shuofei Qiao, Da Zheng, Huajun Chen, and Ningyu Zhang. 2025. Knowrl: Exploring knowledgeable reinforcement learning for factuality. arXiv preprint arXiv:2506.19807.
  45. Youxu Shi, Suorong Yang, and Dong Liu. 2025. Exposing hallucinations to suppress them: Vlms representation editing with generative anchors. arXiv preprint arXiv:2509.21997. — [arXiv:2509.21997](https://arxiv.org/abs/2509.21997) find
  46. Jingran Su, Jingfan Chen, Hongxin Li, Yuntao Chen, Li Qing, and Zhaoxiang Zhang. 2025. Activation steering decoding: Mitigating hallucination in large vision-language models through bidirectional hidden state intervention. In Proceedings of the 63rd Annual Meeting of the Association for Computationa…
  47. Zhiqing Sun, Sheng Shen, Shengcao Cao, Haotian Liu, Chunyuan Li, Yikang Shen, Chuang Gan, Liangyan Gui, Yu-Xiong Wang, Yiming Yang, et al. 2024. Aligning large multimodal models with factually augmented rlhf. In Findings of the Association for Computational Linguistics: ACL 2024, pages 13088– 13110.
  48. Wei Suo, Lijun Zhang, Mengyang Sun, Lin Yuanbo Wu, Peng Wang, and Yanning Zhang. 2025. Octopus: Alleviating hallucination via dynamic contrastive decoding. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 29904–29914. find
  49. Feilong Tang, Chengzhi Liu, Zhongxing Xu, Ming Hu, Zile Huang, Haochen Xue, Ziyang Chen, Zelin Peng, Zhiwei Yang, Sijin Zhou, et al. 2025. Seeing far and clearly: Mitigating hallucinations in mllms with attention causal decoding. In Proceedings of the Computer Vision and Pattern Recognition Conferen… find
  50. Jinfeng Wei and Xiaofeng Zhang. 2024. Dopra: Decoding over-accumulation penalization and re-allocation in specific weighting layer. In Proceedings of the 32nd ACM International Conference on Multimedia, pages 7065–7074. find
  51. Tsung-Han Wu, Heekyung Lee, Jiaxin Ge, Joseph E Gonzalez, Trevor Darrell, and David M Chan. 2025a. Generate, but verify: Reducing hallucination in vision-language models with retrospective resampling. arXiv preprint arXiv:2504.13169. find
  52. Yuanchen Wu, Lu Zhang, Hang Yao, Junlong Du, Ke Yan, Shouhong Ding, Yunsheng Wu, and Xiaoqiang Li. 2025b. Antidote: A unified framework for mitigating lvlm hallucinations in counterfactual presupposition and object perception. In Proceedings of the Computer Vision and Pattern Recognition Conference,… find
  53. Wenyi Xiao, Ziwei Huang, Leilei Gan, Wanggui He, Haoyuan Li, Zhelun Yu, Fangxun Shu, Hao Jiang, and Linchao Zhu. 2025. Detecting and mitigating hallucination in large vision language models via fine-grained ai feedback. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pag… find
  54. Johnathan Xie, Annie S Chen, Yoonho Lee, Eric Mitchell, and Chelsea Finn. 2024. Calibrating language models with adaptive temperature scaling. arXiv preprint arXiv:2409.19817. find
  55. Yun Xing, Yiheng Li, Ivan Laptev, and Shijian Lu. 2024. Mitigating object hallucination via concentric causal attention. Advances in neural information processing systems, 37:92012–92035. find
  56. Yunqiu Xu, Linchao Zhu, and Yi Yang. 2025. Mc-bench: A benchmark for multi-context visual grounding in the era of mllms. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 17675–17687. find
  57. Le Yang, Ziwei Zheng, Boxu Chen, Zhengyu Zhao, Chenhao Lin, and Chao Shen. 2025. Nullu: Mitigating object hallucinations in large vision-language models via halluspace projection. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 14635–14645. find
  58. Zekai Ye, Qiming Li, Xiaocheng Feng, Libo Qin, Yichong Huang, Baohang Li, Kui Jiang, Yang Xiang, Zhirui Zhang, Yunfei Lu, et al. 2025. Claim: Mitigating multilingual object hallucination in large vision-language models with cross-lingual attention intervention. arXiv preprint arXiv:2506.11073. find
  59. Hao Yin, Guangzong Si, and Zilei Wang. 2025. Clearsight: Visual signal enhancement for object hallucination mitigation in multimodal large language models. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 14625–14634. find
  60. Yiyang Zhou, Chenhang Cui, Jaehong Yoon, Linjun Zhang, Zhun Deng, Chelsea Finn, Mohit Bansal, and Huaxiu Yao. 2023. Analyzing and mitigating object hallucination in large vision-language models. arXiv preprint arXiv:2310.00754. find
  61. Lanyun Zhu, Deyi Ji, Tianrun Chen, Peng Xu, Jieping Ye, and Jun Liu. 2025a. Ibd: Alleviating hallucinations in large vision-language models via image-biased decoding. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 1624–1633. find
  62. Younan Zhu, Linwei Tao, Minjing Dong, and Chang Xu. 2025b. Mitigating object hallucinations in large vision-language models via attention calibration. arXiv preprint arXiv:2502.01969. — [arXiv:2502.01969](https://arxiv.org/abs/2502.01969) find
  63. Shukang Yin, Chaoyou Fu, Sirui Zhao, Tong Xu, Hao Wang, Dianbo Sui, Yunhang Shen, Ke Li, Xing Sun, and Enhong Chen. 2024. Woodpecker: Hallucination correction for multimodal large language models. Science China Information Sciences, 67(12):220105. find
  64. Ce Zhang, Zifu Wan, Zhehan Kan, Martin Q Ma, Simon Stepputtis, Deva Ramanan, Russ Salakhutdinov, Louis-Philippe Morency, Katia Sycara, and Yaqi Xie. 2025a. Self-correcting decoding with generative feedback for mitigating hallucinations in large vision-language models. arXiv preprint arXiv:2502.06130… — [arXiv:2502.06130](https://arxiv.org/abs/2502.06130) find
  65. Junyan Zhang, Yiming Huang, Shuliang Liu, Yubo Gao, and Xuming Hu. 2025b. Do bert-like bidirectional models still perform better on text classification in the era of llms? arXiv preprint arXiv:2505.18215. find
  66. Junyan Zhang, Shuliang Liu, Aiwei Liu, Yubo Gao, Jungang Li, Xiaojie Gu, and Xuming Hu. 2025c. Cohemark: A novel sentence-level watermark for enhanced text quality. arXiv preprint arXiv:2504.17309. — [arXiv:2504.17309](https://arxiv.org/abs/2504.17309) find
  67. Fei Zhao, Chengcui Zhang, Runlin Zhang, Tianyang Wang, and Xi Li. 2025a. Mitigating image captioning hallucinations in vision-language models. arXiv preprint arXiv:2505.03420. — [arXiv:2505.03420](https://arxiv.org/abs/2505.03420) find
  68. Jianfei Zhao, Feng Zhang, Xin Sun, and Chong Feng. 2025b. Aligning attention distribution to information flow for hallucination mitigation in large vision-language models. arXiv preprint arXiv:2505.14257. — [arXiv:2505.14257](https://arxiv.org/abs/2505.14257) find
  69. Jianfei Zhao, Feng Zhang, Xin Sun, Lingxing Kong, Zhixing Tan, and Chong Feng. 2025c. Cross-image contrastive decoding: Precise, lossless suppression of language priors in large vision-language models. arXiv preprint arXiv:2505.10634. — [arXiv:2505.10634](https://arxiv.org/abs/2505.10634) find
  70. Linxi Zhao, Yihe Deng, Weitong Zhang, and Quanquan Gu. 2024. Mitigating object hallucination in large vision-language models via image-grounded guidance. arXiv preprint arXiv:2402.08680. — [arXiv:2402.08680](https://arxiv.org/abs/2402.08680) find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/liu-2026-vision-language-introspection-mitigating-overconfident/