Elamur Research⌕
☰
home / papers / 2026 / Revealing and Enhancing Core Visual Regions: Harnessing Internal Attention Dynamics for Hallucination Mitigation in LVLMs

Revealing and Enhancing Core Visual Regions: Harnessing Internal Attention Dynamics for Hallucination Mitigation in LVLMs

Paper · 2026 · Guangtao Lyu, Qi Liu, Chenghao Xu et al.

Summary

Large vision-language models (LVLMs) often hallucinate, producing content that contradicts the image or ignores the user's request. Training-free fixes each have drawbacks. Contrastive decoding needs several forward passes. External expert models add dependencies and possible misalignment. Methods that amplify top-ranked heads or tokens are misled by attention sinks, which are dominant but meaningless tokens. The authors analyse attention in LLaVA-1.5 (7B and 13B). They find that positive changes in attention between consecutive layers mark semantically central image regions, while sinks fluctuate erratically.

They propose PADE, a single-pass, training-free intervention with three parts:

  • It averages these positive inter-layer deltas into a PAD map.
  • It rescales the map per head with Median Absolute Deviation (MAD) so the boost has a sensible size.
  • It applies System-Token Compensation (STC), which takes attention from system-prompt tokens to keep the model focused on instructions and earlier output.

Across several LVLMs and both hallucination-specific and general benchmarks, PADE strengthens visual grounding and reduces hallucination without hurting general multimodal ability. This shows that internal attention dynamics are a usable signal for more reliable models.

Key points

  • PADE is compared against three families of training-free methods:
    • contrastive decoding: VCD, PAI, IBD
    • auxiliary experts: HALC, AGLA
    • static internal signals: VHR, VAF, OPERA, MemVR
  • On CHAIR, removing either MAD or STC lowers performance. Dropping MAD hurts most, because the raw PAD signal is orders of magnitude smaller than attention logits, so without scaling the model behaves almost like the baseline.
  • On CHAIR with LLaVA-1.5 7B and 13B, intervening in later layers works better, and the final layer gives the best results.
  • Small intervention strengths work best: λ = 0.1 is optimal overall and λ = 0.3 is also good, while large λ degrades output.
  • The study is limited to attention. Dynamics of hidden states, FFN activations and logits are left for future work.

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

🔬Institute for Infocomm ResearchSingapore · Singapore43 works · 14,598 citations🏛️Agency for Science, Technology and ResearchSingapore · Singapore30 works · 14,235 citations🎓Xidian UniversityXi'an · China14 works · 1,357 citations🎓Hohai UniversityNanjing · China2 works · 5 citations

 Fields, topics and concepts

📚 Shelves 2The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksComputer Vision and Pattern Recognition · 2,869 works

Cite

Cite as Guangtao Lyu, Qi Liu, Chenghao Xu, Jiexi Yan, Muli Yang, Xueting Li, Fen Fang and Cheng Deng. 2026. Revealing and Enhancing Core Visual Regions: Harnessing Internal Attention Dynamics for Hallucination Mitigation in LVLMs. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.748

@inproceedings{lyu2026revealing,
  title = {{Revealing and Enhancing Core Visual Regions: Harnessing Internal Attention Dynamics for Hallucination Mitigation in LVLMs}},
  author = {Guangtao Lyu, Qi Liu, Chenghao Xu, Jiexi Yan, Muli Yang, Xueting Li, Fen Fang and Cheng Deng},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.748},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.748}
}

References

94 references, 28 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, and 1 others. 2023. Gpt-4 technical report. arXiv:2303.08774.
  2. 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 CVPR. find
  3. Anthropic. 2024. Introducing Claude 3.5 Sonnet. Announcement of Claude 3.5 Sonnet model release, featuring improved intelligence, vision capabilities, and new Artifacts feature. find
  4. Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023. Qwen-vl: A frontier large vision-language model with versatile abilities. arXiv:2308.12966.
  5. Zechen Bai, Pichao Wang, Tianjun Xiao, Tong He, Zongbo Han, Zheng Zhang, and Mike Zheng Shou. 2024. Hallucination of multimodal large language models: A survey. arXiv:2404.18930.
  6. Jinhe Bi, Yifan Wang, Danqi Yan, Xun Xiao, Artur Hecker, Volker Tresp, and Yunpu Ma. 2025a. find
  7. Prism: Self-pruning intrinsic selection method for training-free multimodal data selection. Preprint, arXiv:2502.12119. — [arXiv:2502.12119](https://arxiv.org/abs/2502.12119) find
  8. Jinhe Bi, Yujun Wang, Haokun Chen, Xun Xiao, Artur Hecker, Volker Tresp, and Yunpu Ma. 2025b. Llava steering: Visual instruction tuning with 500x fewer parameters through modality linear representation-steering. In ACL.
  9. Cong Chen, Mingyu Liu, Chenchen Jing, Yizhou Zhou, Fengyun Rao, Hao Chen, Bo Zhang, and Chunhua Shen. 2025. Perturbollava: Reducing multimodal hallucinations with perturbative visual training. In ICLR. find
  10. Junying Chen, Chi Gui, Ruyi Ouyang, Anningzhe Gao, Shunian Chen, Guiming Hardy Chen, Xidong Wang, Zhenyang Cai, Ke Ji, Xiang Wan, and 1 others. 2024a. Towards injecting medical visual knowledge into multimodal llms at scale. In NeurIPS. find
  11. Zhaorun Chen, Zhuokai Zhao, Hongyin Luo, Huaxiu Yao, Bo Li, and Jiawei Zhou. 2024b. Halc: Object hallucination reduction via adaptive focal-contrast decoding. arXiv:2403.00425. — [arXiv:2403.00425](https://arxiv.org/abs/2403.00425) find
  12. Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Muyan Zhong, Qinglong Zhang, Xizhou Zhu, Lewei Lu, and 1 others. 2024c. Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks. In CVPR.
  13. Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E. Gonzalez, Ion Stoica, and Eric P. Xing. 2023. Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. find
  14. Yung-Sung Chuang, Yujia Xie, Hongyin Luo, Yoon Kim, James Glass, and Pengcheng He. 2023. Dola: Decoding by contrasting layers improves factuality in large language models. In ICLR.
  15. Wenliang Dai, Junnan Li, Dongxu Li, Anthony Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale N Fung, and Steven Hoi. 2023. Instructblip: Towards general-purpose vision-language models with instruction tuning. NeurIPS.
  16. Timothée Darcet, Maxime Oquab, Julien Mairal, and Piotr Bojanowski. 2024. Vision transformers need registers. In ICLR. find
  17. DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, and 1 others. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. Preprint, arXiv:2501.12948.
  18. Xin Dong, Shichao Dong, Jin Wang, Jing Huang, Li Zhou, Zenghui Sun, Lihua Jing, Jinsong Lan, Xiaoyong Zhu, and Bo Zheng. 2025. Inter: Mitigating hallucination in large vision-language models by interaction guidance sampling. In CVPR, pages 2534–2544. find
  19. 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 CVPR. find
  20. Huangyw Huangyw, Yong Zhang, Ning Cheng, Zhitao Li, Shaojun Wang, and Jing Xiao. 2025. Dynamic attention-guided context decoding for mitigating context faithfulness hallucinations in large language models. In ACL Findings, pages 5174–5193. find
  21. Chaoyou Fu, Peixian Chen, Yunhang Shen, Yulei Qin, Mengdan Zhang, Xu Lin, Zhenyu Qiu, Wei Lin, Jinrui Yang, Xiawu Zheng, and 1 others. 2023. Mme: A comprehensive evaluation benchmark for multimodal large language models. arXiv:2306.13394.
  22. Fushuo Huo, Wenchao Xu, Zhong Zhang, Haozhao Wang, Zhicheng Chen, and Peilin Zhao. 2024. Self-introspective decoding: Alleviating hallucinations for large vision-language models. arXiv:2408.02032. — [arXiv:2408.02032](https://arxiv.org/abs/2408.02032) find
  23. Boyang Gong, Yu Zheng, Fanye Kong, Jie Zhou, and Jiwen Lu. 2026. Attention at rest stays at rest: Breaking visual inertia for cognitive hallucination mitigation. arXiv preprint arXiv:2604.01989. — [arXiv:2604.01989](https://arxiv.org/abs/2604.01989) find
  24. Tianrui Guan, Fuxiao Liu, Xiyang Wu, Ruiqi Xian, Zongxia Li, Xiaoyu Liu, Xijun Wang, Lichang Chen, Furong Huang, Yaser Yacoob, and 1 others. 2024. Hallusionbench: an advanced diagnostic suite for entangled language hallucination and visual illusion in large vision-language models. In CVPR, pages 143…
  25. Anisha Gunjal, Jihan Yin, and Erhan Bas. 2024. Detecting and preventing hallucinations in large vision language models. In AAAI, 16. find
  26. Danna Gurari, Qing Li, Abigale J Stangl, Anhong Guo, Chi Lin, Kristen Grauman, Jiebo Luo, and Jeffrey P Bigham. 2018. Vizwiz grand challenge: Answering visual questions from blind people. In CVPR, pages 3608–3617. find
  27. 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 ACL.
  28. Shengding Hu, Yuge Tu, Xu Han, Chaoqun He, Ganqu Cui, Xiang Long, Zhi Zheng, Yewei Fang, Yuxiang Huang, Weilin Zhao, and 1 others. 2024a. Minicpm: Unveiling the potential of small language models with scalable training strategies. arXiv:2404.06395.
  29. Yutao Hu, Tianbin Li, Quanfeng Lu, Wenqi Shao, Junjun He, Yu Qiao, and Ping Luo. 2024b. Omnimedvqa: A new large-scale comprehensive evaluation benchmark for medical lvlm. In CVPR. find
  30. Lei Huang, Xiaocheng Feng, Weitao Ma, Yuchun Fan, Xiachong Feng, Yuxuan Gu, Yangfan Ye, Liang Zhao, Weihong Zhong, Baoxin Wang, and 1 others. 2025. Alleviating hallucinations from knowledge misalignment in large language models via selective abstention learning. In ACL, pages 24564–24579. find
  31. Qidong Huang, Xiaoyi Dong, Pan Zhang, Bin Wang, Conghui He, Jiaqi Wang, Dahua Lin, Weiming Zhang, and Nenghai Yu. 2023. Opera: Alleviating hallucination in multi-modal large language models via over-trust penalty and retrospection-allocation. arXiv:2311.17911. find
  32. Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Ye Jin Bang, Andrea Madotto, and Pascale Fung. 2023. Survey of hallucination in natural language generation. ACM Computing Surveys.
  33. Bo Jiang, Shaoyu Chen, Bencheng Liao, Xingyu Zhang, Wei Yin, Qian Zhang, Chang Huang, Wenyu Liu, and Xinggang Wang. 2024. Senna: Bridging large vision-language models and end-to-end autonomous driving. arXiv:2410.22313. — [arXiv:2410.22313](https://arxiv.org/abs/2410.22313) find
  34. Nicholas Jiang, Anish Kachinthaya, Suzanne Petryk, and Yossi Gandelsman. Interpreting and editing vision-language representations to mitigate hallucinations. In ICLR. find
  35. Nick Jiang, Amil Dravid, Alexei Efros, and Yossi Gandelsman. 2025a. Vision transformers don’t need trained registers. In NeurIPS. find
  36. Zhangqi Jiang, Junkai Chen, Beier Zhu, Tingjin Luo, Yankun Shen, and Xu Yang. 2025b. Devils in middle layers of large vision-language models: Interpreting, detecting and mitigating object hallucinations via attention lens. In CVPR. find
  37. Seil Kang, Jinyeong Kim, Junhyeok Kim, and Seong Jae Hwang. 2025. See what you are told: Visual attention sink in large multimodal models. arXiv:2503.03321. — [arXiv:2503.03321](https://arxiv.org/abs/2503.03321) find
  38. Samir Khaki, Junxian Guo, Jiaming Tang, Shang Yang, Yukang Chen, Konstantinos N Plataniotis, Yao Lu, Song Han, and Zhijian Liu. Sparsevila-r1: Decoupling visual sparsity for efficient vlm reasoning. In NeurIPS 2025 Workshop on Efficient Reasoning. find
  39. Samir Khaki, Junxian Guo, Jiaming Tang, Shang Yang, Yukang Chen, Konstantinos N Plataniotis, Yao Lu, Song Han, and Zhijian Liu. 2025. Sparsevila: Decoupling visual sparsity for efficient vlm inference. In ICCV, pages 23784–23794. find
  40. Junho Kim, Hyunjun Kim, Kim Yeonju, and Yong Man Ro. 2024. Code: Contrasting self-generated description to combat hallucination in large multi-modal models. NeurIPS, 37:133571–133599. find
  41. Katherine Lee, Orhan Firat, Ashish Agarwal, Clara Fannjiang, and David Sussillo. 2018. Hallucinations in neural machine translation. find
  42. 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 CVPR.
  43. Wei Li, Zhen Huang, Houqiang Li, Le Lu, Yang Lu, Xinmei Tian, Xu Shen, and Jieping Ye. 2025. Visual evidence prompting mitigates hallucinations in large vision-language models. In ACL, pages 4048–4080. find
  44. Yifan Li, Yifan Du, Kun Zhou, Jinpeng Wang, Wayne Xin Zhao, and Ji-Rong Wen. 2023. Evaluating object hallucination in large vision-language models. arXiv:2305.10355.
  45. Bin Lin, Yang Ye, Bin Zhu, Jiaxi Cui, Munan Ning, Peng Jin, and Li Yuan. 2024. Video-llava: Learning united visual representation by alignment before projection. In EMNLP.
  46. Fuxiao Liu, Kevin Lin, Linjie Li, Jianfeng Wang, Yaser Yacoob, and Lijuan Wang. 2024a. Mitigating hallucination in large multi-modal models via robust instruction tuning. In ICLR.
  47. Hanchao Liu, Wenyuan Xue, Yifei Chen, Dapeng Chen, Xiutian Zhao, Ke Wang, Liping Hou, Rongjun Li, and Wei Peng. 2024b. A survey on hallucination in large vision-language models. arXiv:2402.00253. find
  48. Haotian Liu, Chunyuan Li, Yuheng Li, Bo Li, Yuanhan Zhang, Sheng Shen, and Yong Jae Lee. 2024c. Llavanext: Improved reasoning, ocr, and world knowledge. find
  49. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. In NeurIPS.
  50. Shi Liu, Kecheng Zheng, and Wei Chen. 2024d. Paying more attention to image: A training-free method for alleviating hallucination in lvlms. arXiv:2407.21771. — [arXiv:2407.21771](https://arxiv.org/abs/2407.21771) find
  51. Shiyu Liu, Xinyi Wen, Zhibin Lan, Ante Wang, and Jinsong Su. 2026. Countering the over-reliance trap: Mitigating object hallucination for lvlms via a self-validation framework. arXiv preprint arXiv:2601.22451. — [arXiv:2601.22451](https://arxiv.org/abs/2601.22451) find
  52. Yexin Liu, Zhengyang Liang, Yueze Wang, Xianfeng Wu, Feilong Tang, Muyang He, Jian Li, Zheng Liu, Harry Yang, Sernam Lim, and 1 others. 2025a. Unveiling the ignorance of mllms: Seeing clearly, answering incorrectly. In CVPR. find
  53. Zhining Liu, Ziyi Chen, Hui Liu, Chen Luo, Xianfeng Tang, Suhang Wang, Joy Zeng, Zhenwei Dai, Zhan Shi, Tianxin Wei, and 1 others. 2025b. Seeing but not believing: Probing the disconnect between visual attention and answer correctness in vlms. arXiv:2510.17771. — [arXiv:2510.17771](https://arxiv.org/abs/2510.17771) find
  54. Haoyu Lu, Wen Liu, Bo Zhang, Bingxuan Wang, Kai Dong, Bo Liu, Jingxiang Sun, Tongzheng Ren, Zhuoshu Li, Yaofeng Sun, and 1 others. 2024. Deepseek-vl: towards real-world vision-language understanding. arXiv:2403.05525.
  55. Guangtao Lyu, Xinyi Cheng, Chenghao Xu, Qi Liu, Muli Yang, Fen Fang, Huilin Chen, Jiexi Yan, Xu Yang, and Cheng Deng. 2025a. Revealing perception and generation dynamics in lvlms: Mitigating hallucinations via validated dominance correction. arXiv:2512.18813. — [arXiv:2512.18813](https://arxiv.org/abs/2512.18813) find
  56. Guangtao Lyu, Chenghao Xu, Jiexi Yan, Muli Yang, and Cheng Deng. 2025b. Towards unified human motion-language understanding via sparse interpretable characterization. In ICLR. find
  57. Yassine Ouali, Adrian Bulat, Brais Martinez, and Georgios Tzimiropoulos. 2024. Clip-dpo: Vision-language models as a source of preference for fixing hallucinations in lvlms. In ECCV, pages 395–413. find
  58. Woohyeon Park, Woojin Kim, Jaeik Kim, and Jaeyoung Do. 2025. Second: Mitigating perceptual hallucination in vision-language models via selective and contrastive decoding. In ICML. find
  59. Zheng Qi, Chao Shang, Evangelia Spiliopoulou, and Nikolaos Pappas. 2025. Capturing gaze shifts for guidance: Cross-modal fusion enhancement for vlm hallucination mitigation. arXiv:2510.22067. — [arXiv:2510.22067](https://arxiv.org/abs/2510.22067) find
  60. Anna Rohrbach, Lisa Anne Hendricks, Kaylee Burns, Trevor Darrell, and Kate Saenko. 2018. Object hallucination in image captioning. arXiv:1809.02156.
  61. Hao Shao, Yuxuan Hu, Letian Wang, Guanglu Song, Steven L Waslander, Yu Liu, and Hongsheng Li. 2024. Lmdrive: Closed-loop end-to-end driving with large language models. In CVPR. find
  62. Fengzhao Sun, Jun Yu, Yunxiang Zhang, Jiaming Hou, Xilong Lu, Heng Song, and Fang Gao. 2025a. Towards robust autonomous driving: Conditional multimodal large language models for fine-grained perception. In ICRA. find
  63. Guohao Sun, Can Qin, Huazhu Fu, Linwei Wang, and Zhiqiang Tao. 2024a. Self-training large language and vision assistant for medical question answering. NeurIPS. find
  64. Mingjie Sun, Xinlei Chen, J Zico Kolter, and Zhuang Liu. 2024b. Massive activations in large language models. arXiv:2402.17762. find
  65. Nan Sun, Zhenyu Zhang, Xixun Lin, Kun Wang, Yanmin Shang, Naibin Gu, Shuohuan Wang, Yu Sun, Hua Wu, Haifeng Wang, and 1 others. 2025b. V-iti: Mitigating hallucinations in multimodal large language models via visual inference-time intervention. arXiv:2512.03542. — [arXiv:2512.03542](https://arxiv.org/abs/2512.03542) find
  66. Feilong Tang, Chengzhi Liu, Zhongxing Xu, Ming Hu, Zile Huang, Haochen Xue, Ziyang Chen, Zelin Peng, Zhiwei Yang, Sijin Zhou, and 1 others. 2025. Seeing far and clearly: Mitigating hallucinations in mllms with attention causal decoding. In CVPR, pages 26147–26159. find
  67. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, and 1 others. 2023. Llama: Open and efficient foundation language models. arXiv:2302.13971.
  68. Zifu Wan, Ce Zhang, Silong Yong, Martin Q Ma, Simon Stepputtis, Louis-Philippe Morency, Deva Ramanan, Katia Sycara, and Yaqi Xie. 2025. Only: One-layer intervention sufficiently mitigates hallucinations in large vision-language models. arXiv:2507.00898. — [arXiv:2507.00898](https://arxiv.org/abs/2507.00898) find
  69. Junqi Yang, Yuecong Min, Jie Zhang, Shiguang Shan, and Xilin Chen. 2026. Infact: A diagnostic benchmark for induced faithfulness and factuality hallucinations in video-llms. arXiv preprint arXiv:2603.11481.
  70. Chenxi Wang, Xiang Chen, Ningyu Zhang, Bozhong Tian, Haoming Xu, Shumin Deng, and Huajun Chen. 2024a. Mllm can see? dynamic correction decoding for hallucination mitigation. arXiv:2410.11779. — [arXiv:2410.11779](https://arxiv.org/abs/2410.11779) find
  71. Tianyun Yang, Ziniu Li, Juan Cao, and Chang Xu. 2025b. Mitigating hallucination in large vision-language models via modular attribution and intervention. In Adaptive Foundation Models: Evolving AI for Personalized and Efficient Learning. find
  72. Fei Wang, Xingchen Wan, Ruoxi Sun, Jiefeng Chen, and Sercan O Arik. 2025. Astute rag: Overcoming imperfect retrieval augmentation and knowledge conflicts for large language models. In ACL.
  73. Junyang Wang, Yuhang Wang, Guohai Xu, Jing Zhang, Yukai Gu, Haitao Jia, Jiaqi Wang, Haiyang Xu, Ming Yan, Ji Zhang, and 1 others. 2023. Amber: An llm-free multi-dimensional benchmark for mllms hallucination evaluation. arXiv:2311.07397. find
  74. Xintong Wang, Jingheng Pan, Liang Ding, and Chris Biemann. 2024b. Mitigating hallucinations in large vision-language models with instruction contrastive decoding. In ACL. find
  75. Sangmin Woo, Donguk Kim, Jaehyuk Jang, Yubin Choi, and Changick Kim. 2025. Don’t miss the forest for the trees: Attentional vision calibration for large vision language models. In ACL Findings. find
  76. Guangxuan Xiao, Yuandong Tian, Beidi Chen, Song Han, and Mike Lewis. 2023. Efficient streaming language models with attention sinks. arXiv:2309.17453. find
  77. Yun Xing, Yiheng Li, Ivan Laptev, and Shijian Lu. 2024. Mitigating object hallucination via concentric causal attention. NeurIPS, 37:92012–92035. find
  78. Chenghao Xu, Lyu Guangtao, Yan Jiexi, Yang Muli, and Cheng Deng. 2024. Llm knows body language, too: Translating speech voices into human gestures. In ACL. find
  79. Chenghao Xu, Jiexi Yan, Muli Yang, Fen Fang, Huilin Chen, and Cheng Deng. 2026a. Editing is a bargaining game: Balanced knowledge editing in large language models. In AAAI, volume 40, pages 34097– 34105. find
  80. Shijia Xu, Zhou Wu, Xiaolong Jia, Yu Wang, Kai Liu, and April Xiaowen Dong. 2026b. Self-correcting rag: Enhancing faithfulness via mmkp context selection and nli-guided mcts. arXiv:2604.10734.
  81. Bei Yan, Yuecong Min, Jie Zhang, Shiguang Shan, and Xilin Chen. 2026. Act now: Preempting lvlm hallucinations via adaptive context integration. arXiv preprint arXiv:2604.00983. — [arXiv:2604.00983](https://arxiv.org/abs/2604.00983) find
  82. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, and 1 others. 2025a. Qwen3 technical report. arXiv:2505.09388.
  83. Qinghao Ye, Haiyang Xu, Jiabo Ye, Ming Yan, Anwen Hu, Haowei Liu, Qi Qian, Ji Zhang, and Fei Huang. 2024. mplug-owl2: Revolutionizing multi-modal large language model with modality collaboration. In CVPR.
  84. Hao Yin, Guangzong Si, and Zilei Wang. 2025. Clearsight: Visual signal enhancement for object hallucination mitigation in multimodal large language models. In CVPR, pages 14625–14634. find
  85. Shukang Yin, Chaoyou Fu, Sirui Zhao, Tong Xu, Hao Wang, Dianbo Sui, Yunhang Shen, Ke Li, Xing Sun, and Enhong Chen. 2023. Woodpecker: Hallucination correction for multimodal large language models. arXiv:2310.16045. find
  86. Tianyu Yu, Yuan Yao, Haoye Zhang, Taiwen He, Yifeng Han, Ganqu Cui, Jinyi Hu, Zhiyuan Liu, Hai-Tao Zheng, Maosong Sun, and 1 others. 2024a. Rlhf-v: Towards trustworthy mllms via behavior alignment from fine-grained correctional human feedback. In CVPR, pages 13807–13816. find
  87. Tianyu Yu, Haoye Zhang, Yuan Yao, Yunkai Dang, Da Chen, Xiaoman Lu, Ganqu Cui, Taiwen He, Zhiyuan Liu, Tat-Seng Chua, and 1 others. 2024b. Rlaif-v: Aligning mllms through open-source ai feedback for super gpt-4v trustworthiness. find
  88. Weihao Yu, Zhengyuan Yang, Linjie Li, Jianfeng Wang, Kevin Lin, Zicheng Liu, Xinchao Wang, and Lijuan Wang. 2023. Mm-vet: Evaluating large multimodal models for integrated capabilities. arXiv:2308.02490.
  89. Xiaofeng Zhang, Yihao Quan, Chaochen Gu, Chen Shen, Xiaosong Yuan, Shaotian Yan, Hao Cheng, Kaijie Wu, and Jieping Ye. 2024. Seeing clearly by layer two: Enhancing attention heads to alleviate hallucination in lvlms. arXiv:2411.09968. — [arXiv:2411.09968](https://arxiv.org/abs/2411.09968) find
  90. Yongheng Zhang, Xu Liu, Ruoxi Zhou, Qiguang Chen, Hao Fei, Wenpeng Lu, and Libo Qin. 2025. Cchall: A novel benchmark for joint cross-lingual and cross-modal hallucinations detection in large language models. ACL. find
  91. Yiyang Zhou, Chenhang Cui, Jaehong Yoon, Linjun Zhang, Zhun Deng, Chelsea Finn, Mohit Bansal, and Huaxiu Yao. 2024. Analyzing and mitigating object hallucination in large vision-language models. In ICLR. find
  92. Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2023. Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv:2304.10592.
  93. Lanyun Zhu, Deyi Ji, Tianrun Chen, Peng Xu, Jieping Ye, and Jun Liu. 2024. Ibd: Alleviating hallucinations in large vision-language models via image-biased decoding. arXiv:2402.18476. — [arXiv:2402.18476](https://arxiv.org/abs/2402.18476) find
  94. Xin Zou, Yizhou Wang, Yibo Yan, Sirui Huang, Kening Zheng, Junkai Chen, Chang Tang, and Xuming Hu. 2025. Look twice before you answer: Memory-space visual retracing for hallucination mitigation in multimodal large language models. In ICML. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/lyu-2026-revealing-enhancing-core-visual-regions/