Elamur Research⌕
☰
home / papers / 2026 / Journey Before Destination: On the importance of Visual Faithfulness in Slow Thinking

Journey Before Destination: On the importance of Visual Faithfulness in Slow Thinking

Paper · 2026 · Rheeya Uppaal, Phu Mon Htut, Min Bai et al.

Summary

Reasoning-trained vision–language models (VLMs) write out long chains of thought. Benchmarks usually check only whether the final answer is right. The authors show this misses a separate failure mode. A model can reach a correct answer while describing things that are not in the image, or it can read the image correctly and still go wrong in later logic.

They treat visual faithfulness of the reasoning chain as its own evaluation axis. Their framework needs no training and no reference annotations. It splits a chain into perception steps and reasoning steps, then asks off-the-shelf VLM judges whether each perception step is supported by the image. A human meta-evaluation checks that this judging is reliable. The resulting metric is the Unfaithful Perception Rate (UPR).

They also propose a training-free self-reflection loop. A detector decides when a perception step is unfaithful, and only that step is regenerated. On perception-heavy benchmarks, this lowers UPR without hurting final-answer accuracy, and accuracy often improves. The work matters because it makes multimodal reasoning more transparent and trustworthy, not just accurate.

Key points

  • Benchmarks and models: Evaluation covers MMEval-Pro, HallusionBench and MMVP, mainly with ThinkLite-VL. The authors report the trend also holds for other reasoning-trained VLMs.

  • Choosing the detector: About 1200 samples were drawn from the perception split of MMEval-Pro, with 500 held out for tuning. Gold labels came from Claude 4 Sonnet.

    • White-box (internal-signal) detectors and trained detectors did poorly.
    • Auxiliary-VLM judges achieved the best F1 and were adopted.

  • Results on MMVP:

    DetectorUPRAccuracy
    None (vanilla)8.4%35.0%
    Claude 3.7 Sonnet1.7%39.7%
    Qwen2.5-VL-72B-Instruct2.1%32.0%
    Model's own self-assessment6.5%33.3%

  • Cost of regeneration: Regeneration is capped at three attempts. Most unfaithful steps are fixed on the first retry, and over 90% of successful fixes happen within three.

  • Limitations:

    • Extra forward passes add latency.
    • The method depends on a strong external judge model.
    • The scope is limited to perception-heavy tasks.

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

 Fields, topics and concepts

📚 Shelves 7The 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 worksPsychology · 1,552 worksExperimental and Cognitive Psychology · 870 works

🧭 Topics 1Research subjects and languages the work is about.Reasoning · 1,426 works

Cite

Cite as Rheeya Uppaal, Phu Mon Htut, Min Bai, Nikolaos Pappas, Zheng Qi and Sandesh Swamy. 2026. Journey Before Destination: On the importance of Visual Faithfulness in Slow Thinking. Proceedings of the 19th Conference of the European Chapter 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.eacl-long.194

@inproceedings{uppaal2026journey,
  title = {{Journey Before Destination: On the importance of Visual Faithfulness in Slow Thinking}},
  author = {Rheeya Uppaal, Phu Mon Htut, Min Bai, Nikolaos Pappas, Zheng Qi and Sandesh Swamy},
  booktitle = {Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.eacl-long.194},
  url = {https://doi.org/10.18653/v1/2026.eacl-long.194}
}

References

91 references, 22 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. AI Anthropic. 2024. The claude 3 model family: Opus, sonnet, haiku. Claude-3 Model Card, 1(1):4. find
  2. Kazi Hasan Ibn Arif, Sajib Acharjee Dip, Khizar Hussain, Lang Zhang, and Chris Thomas. 2025. Paint: Paying attention to informed tokens to mitigate hallucination in large vision-language model. arXiv preprint arXiv:2501.12206. — [arXiv:2501.12206](https://arxiv.org/abs/2501.12206) find
  3. Malika Aubakirova, Alex Atallah, Chris Clark, Justin Summerville, and Anjney Midha. 2025. State of ai: An empirical 100 trillion token study with openrouter. find
  4. The 2025 State of AI Report. find
  5. Amos Azaria and Tom Mitchell. 2023. The internal state of an llm knows when it’s lying. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 967–976.
  6. Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, and 1 others. 2025. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923. — Qwen2.5-VL Technical Report
  7. 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 preprint arXiv:2404.18930.
  8. Yangyi Chen, Karan Sikka, Michael Cogswell, Heng Ji, and Ajay Divakaran. 2024. Measuring and improving chain-of-thought reasoning in vision-language models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologi… find
  9. Zhiyuan Chen, Yuecong Min, Jie Zhang, Bei Yan, Jiahao Wang, Xiaozhen Wang, and Shiguang Shan. 2025. A survey of multimodal hallucination evaluation and detection. arXiv preprint arXiv:2507.19024. — [arXiv:2507.19024](https://arxiv.org/abs/2507.19024) find
  10. Kanzhi Cheng, Li YanTao, Fangzhi Xu, Jianbing Zhang, Hao Zhou, and Yang Liu. 2025. Vision-language models can self-improve reasoning via reflection. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technolog…
  11. Jacob Cohen. 1960. A coefficient of agreement for nominal scales. Educational and psychological measurement, 20(1):37–46. find
  12. Yihe Deng, Hritik Bansal, Fan Yin, Nanyun Peng, Wei Wang, and Kai-Wei Chang. 2025. Openvlthinker: An early exploration to complex vision-language reasoning via iterative self-improvement. arXiv preprint arXiv:2503.17352. — [arXiv:2503.17352](https://arxiv.org/abs/2503.17352) find
  13. Yihe Deng, Pan Lu, Fan Yin, Ziniu Hu, Sheng Shen, Quanquan Gu, James Y Zou, Kai-Wei Chang, and Wei Wang. 2024. Enhancing large vision language models with self-training on image comprehension. Advances in Neural Information Processing Systems, 37:131369–131397. find
  14. Xuefeng Du, Chaowei Xiao, and Sharon Li. 2024. Haloscope: Harnessing unlabeled llm generations for hallucination detection. Advances in Neural Information Processing Systems, 37:102948–102972. find
  15. Sebastian Farquhar, Jannik Kossen, Lorenz Kuhn, and Yarin Gal. 2024. Detecting hallucinations in large language models using semantic entropy. Nature, 630(8017):625–630. find
  16. 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
  17. Joseph L Fleiss. 1971. Measuring nominal scale agreement among many raters. Psychological bulletin, 76(5):378. find
  18. Sreyan Ghosh, Chandra Kiran Reddy Evuru, Sonal Kumar, Utkarsh Tyagi, Oriol Nieto, Zeyu Jin, and Dinesh Manocha. 2024. Visual description grounding reduces hallucinations and boosts reasoning in lvlms. In The Thirteenth International Conference on Learning Representations. find
  19. Sachin Goyal, Christina Baek, J Zico Kolter, and Aditi Raghunathan. 2025. Context-parametric inversion: Why instruction finetuning can worsen context reliance. In ICLR 2025 Workshop on Navigating and Addressing Data Problems for Foundation Models. find
  20. 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 Proceedings of…
  21. Anisha Gunjal, Jihan Yin, and Erhan Bas. 2023. Detecting and preventing hallucinations in large vision language models. arxiv preprint abs/2308.06394 (2023). find
  22. Shibo Hao, Yi Gu, Haotian Luo, Tianyang Liu, Xiyan Shao, Xinyuan Wang, Shuhua Xie, Haodi Ma, Adithya Samavedhi, Qiyue Gao, and 1 others. 2024. Llm reasoners: New evaluation, library, and analysis of step-by-step reasoning with large language models. In First Conference on Language Modeling. find
  23. Rui Hu, Yahan Tu, Shuyu Wei, Dongyuan Lu, and Jitao Sang. 2025. Prescribing the right remedy: Mitigating hallucinations in large vision-language models via targeted instruction tuning. Information Sciences, page 122361. find
  24. Jinsheng Huang, Liang Chen, Taian Guo, Fu Zeng, Yusheng Zhao, Bohan Wu, Ye Yuan, Haozhe Zhao, Zhihui Guo, Yichi Zhang, and 1 others. 2025. Mmevalpro: Calibrating multimodal benchmarks towards trustworthy and efficient evaluation. In Proceedings of the 2025 Conference of the Nations of the Americas C… find
  25. 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
  26. Alon Jacovi, Yonatan Bitton, Bernd Bohnet, Jonathan Herzig, Michael Tseng, Michael Collins, Roee Aharoni, and Mor Geva Pipek. 2024. A chain-of-thought is as strong as its weakest link: A benchmark for verifiers of reasoning chains. In Proceedings of the 62nd Annual Meeting of the Association for Com…
  27. Nicholas Jiang, Anish Kachinthaya, Suzanne Petryk, and Yossi Gandelsman. 2025. Interpreting and editing vision-language representations to mitigate hallucinations. In The Thirteenth International Conference on Learning Representations. find
  28. Liqiang Jing and Xinya Du. 2024. Fgaif: Aligning large vision-language models with fine-grained ai feedback. Transactions on Machine Learning Research. find
  29. Liqiang Jing, Ruosen Li, Yunmo Chen, and Xinya Du. 2024. Faithscore: Fine-grained evaluations of hallucinations in large vision-language models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 5042–5063. find
  30. 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
  31. Jan-Christoph Klie, Richard Eckart de Castilho, and Iryna Gurevych. 2024. Analyzing dataset annotation quality management in the wild. Computational Linguistics, 50(3):817–866.
  32. Gary G Koch. 2004. Intraclass correlation coefficient. Encyclopedia of statistical sciences. find
  33. Terry K Koo and Mae Y Li. 2016. A guideline of selecting and reporting intraclass correlation coefficients for reliability research. Journal of chiropractic medicine, 15(2):155–163. find
  34. Yifan Li, Yifan Du, Kun Zhou, Jinpeng Wang, Wayne Xin Zhao, and Ji-Rong Wen. 2023. Evaluating object hallucination in large vision-language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 292–305.
  35. Zhong-Zhi Li, Duzhen Zhang, Ming-Liang Zhang, Jiaxin Zhang, Zengyan Liu, Yuxuan Yao, Haotian Xu, Junhao Zheng, Pei-Jie Wang, Xiuyi Chen, and 1 others. 2025. From system 1 to system 2: A survey of reasoning large language models. CoRR.
  36. Chengzhi Liu, Zhongxing Xu, Qingyue Wei, Juncheng Wu, James Zou, Xin Eric Wang, Yuyin Zhou, and Sheng Liu. 2025a. More thinking, less seeing? assessing amplified hallucination in multimodal reasoning models. arXiv preprint arXiv:2505.21523. — [arXiv:2505.21523](https://arxiv.org/abs/2505.21523) find
  37. 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 The Twelfth International Conference on Learning Representations.
  38. Cong-Duy Nguyen, Xiaobao Wu, Duc Anh Vu, Shuai Zhao, Thong Nguyen, and Anh Tuan Luu. 2025. Cut-paste&find: Efficient multimodal hallucination detector with visual-aid knowledge base. arXiv preprint arXiv:2502.12591. — [arXiv:2502.12591](https://arxiv.org/abs/2502.12591) find
  39. 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. CoRR. find
  40. Letitia Parcalabescu and Anette Frank. 2025. Do vision & language decoders use images and text equally? how self-consistent are their explanations? In The Thirteenth International Conference on Learning Representations. find
  41. Haotian Liu, Chunyuan Li, Yuheng Li, Bo Li, Yuanhan Zhang, Sheng Shen, and Yong Jae Lee. 2024c. Lla-vanext: Improved reasoning, ocr, and world knowledge. find
  42. Sheng Liu, Haotian Ye, and James Zou. 2025b. Reducing hallucinations in large vision-language models via latent space steering. In The Thirteenth International Conference on Learning Representations. find
  43. Shilong Liu, Zhaoyang Zeng, Tianhe Ren, Feng Li, Hao Zhang, Jie Yang, Qing Jiang, Chunyuan Li, Jianwei Yang, Hang Su, and 1 others. 2024d. Grounding dino: Marrying dino with grounded pre-training for open-set object detection. In European conference on computer vision, pages 38–55. Springer.
  44. Yuan Liu, Haodong Duan, Yuanhan Zhang, Bo Li, Songyang Zhang, Wangbo Zhao, Yike Yuan, Jiaqi Wang, Conghui He, Ziwei Liu, and 1 others. 2024e. Mmbench: Is your multi-modal model an all-around player? In European conference on computer vision, pages 216–233. Springer.
  45. LMArena. 2024. The multimodal arena is here! LM Arena Blog. find
  46. Pan Lu, Hritik Bansal, Tony Xia, Jiacheng Liu, Chunyuan Li, Hannaneh Hajishirzi, Hao Cheng, Kai-Wei Chang, Michel Galley, and Jianfeng Gao. 2024. Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts. In The Twelfth International Conference on Learning Representations.
  47. Pan Lu, Swaroop Mishra, Tanglin Xia, Liang Qiu, Kai-Wei Chang, Song-Chun Zhu, Oyvind Tafjord, Peter Clark, and Ashwin Kalyan. 2022. Learn to explain: Multimodal reasoning via thought chains for science question answering. Advances in Neural Information Processing Systems, 35:2507–2521. find
  48. Fanqing Meng, Lingxiao Du, Zongkai Liu, Zhixiang Zhou, Quanfeng Lu, Daocheng Fu, Botian Shi, Wenhai Wang, Junjun He, Kaipeng Zhang, and 1 others. 2025. Mm-eureka: Exploring visual aha moment with rule-based large-scale reinforcement learning. CoRR. find
  49. Lingfeng Ming, Yadong Li, Song Chen, Jianhua Xu, Zenan Zhou, and Weipeng Chen. 2025. Ocean-r1: An open and generalizable large vision-language model enhanced by reinforcement learning. find
  50. Yuankai Qi, Qi Wu, Peter Anderson, Xin Wang, William Yang Wang, Chunhua Shen, and Anton van den Hengel. 2020. Reverie: Remote embodied visual referring expression in real indoor environments. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9982–9991. find
  51. Pooyan Rahmanzadehgervi, Logan Bolton, Mohammad Reza Taesiri, and Anh Totti Nguyen. 2024. Vision language models are blind: Failing to translate detailed visual features into words. arXiv preprint arXiv:2407.06581. find
  52. Parshin Shojaee, Iman Mirzadeh, Keivan Alizadeh, Maxwell Horton, Samy Bengio, and Mehrdad Farajtabar. 2025. The illusion of thinking: Understanding the strengths and limitations of reasoning models via the lens of problem complexity. arXiv preprint arXiv:2506.06941. find
  53. 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…
  54. Zhiqing Sun, Sheng Shen, Shengcao Cao, Haotian Liu, Chunyuan Li, Yikang Shen, Chuang Gan, Liangyan Gui, Yu-Xiong Wang, Yiming Yang, and 1 others. 2024a. Aligning large multimodal models with factually augmented rlhf. In Findings of the Association for Computational Linguistics ACL 2024, pages 13088–…
  55. Zhiqing Sun, Sheng Shen, Shengcao Cao, Haotian Liu, Chunyuan Li, Yikang Shen, Chuang Gan, Liangyan Gui, Yu-Xiong Wang, Yiming Yang, and 1 others. 2024b. Aligning large multimodal models with factually augmented rlhf. In Findings of the Association for Computational Linguistics ACL 2024, pages 13088–…
  56. ZhongXiang Sun, Xiaoxue Zang, Kai Zheng, Jun Xu, Xiao Zhang, Weijie Yu, Yang Song, and Han Li. 2024c. Redeep: Detecting hallucination in retrieval-augmented generation via mechanistic interpretability. In The Thirteenth International Conference on Learning Representations. find
  57. Qwen Team. 2024. Qwen2 technical report. arXiv preprint arXiv:2407.10671, 2. find
  58. Shengbang Tong, Zhuang Liu, Yuexiang Zhai, Yi Ma, Yann LeCun, and Saining Xie. 2024. Eyes wide shut? exploring the visual shortcomings of multimodal llms. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9568–9578.
  59. Rheeya Uppaal, Apratim Dey, Yiting He, Yiqiao Zhong, and Junjie Hu. 2025. Model editing as a robust and denoised variant of dpo: A case study on toxicity. In The Thirteenth International Conference on Learning Representations. find
  60. Rheeya Uppaal, Junjie Hu, and Yixuan Li. 2023. Is fine-tuning needed? pre-trained language models are near perfect for out-of-domain detection. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12813–12832. find
  61. Bin Wang, Fan Wu, Xiao Han, Jiahui Peng, Huaping Zhong, Pan Zhang, Xiaoyi Dong, Weijia Li, Wei Li, Jiaqi Wang, and 1 others. 2024a. Vigc: Visual instruction generation and correction. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 5309–5317. find
  62. Haozhe Wang, Chao Qu, Zuming Huang, Wei Chu, Fangzhen Lin, and Wenhu Chen. 2025a. Vl-rethinker: Incentivizing self-reflection of vision-language models with reinforcement learning. arXiv preprint arXiv:2504.08837. find
  63. Jiaqi Wang, Yifei Gao, and Jitao Sang. 2024b. Valid: Mitigating the hallucination of large vision language models by visual layer fusion contrastive decoding. arXiv preprint arXiv:2411.15839. — [arXiv:2411.15839](https://arxiv.org/abs/2411.15839) find
  64. Junyang Wang, Yuhang Wang, Guohai Xu, Jing Zhang, Yukai Gu, Haitao Jia, Jiaqi Wang, Haiyang Xu, Ming Yan, Ji Zhang, and 1 others. 2023a. Amber: An llm-free multi-dimensional benchmark for mllms hallucination evaluation. arXiv preprint arXiv:2311.07397. find
  65. Junyang Wang, Yuhang Wang, Guohai Xu, Jing Zhang, Yukai Gu, Haitao Jia, Ming Yan, Ji Zhang, and Jitao Sang. 2023b. An llm-free multi-dimensional benchmark for mllms hallucination evaluation. CoRR. find
  66. Junyang Wang, Yiyang Zhou, Guohai Xu, Pengcheng Shi, Chenlin Zhao, Haiyang Xu, Qinghao Ye, Ming Yan, Ji Zhang, Jihua Zhu, and 1 others. 2023c. Evaluation and analysis of hallucination in large vision-language models. arXiv preprint arXiv:2308.15126. — [arXiv:2308.15126](https://arxiv.org/abs/2308.15126) find
  67. Ke Wang, Junting Pan, Weikang Shi, Zimu Lu, Houxing Ren, Aojun Zhou, Mingjie Zhan, and Hongsheng Li. 2024c. Measuring multimodal mathematical reasoning with math-vision dataset. Advances in Neural Information Processing Systems, 37:95095–95169.
  68. Xiyao Wang, Zhengyuan Yang, Chao Feng, Hongjin Lu, Linjie Li, Chung-Ching Lin, Kevin Lin, Furong Huang, and Lijuan Wang. 2025b. Sota with less: Mcts-guided sample selection for data-efficient visual reasoning self-improvement. arXiv preprint arXiv:2504.07934. — [arXiv:2504.07934](https://arxiv.org/abs/2504.07934) find
  69. Yibin Wang, Yuhang Zang, Hao Li, Cheng Jin, and Jiaqi Wang. 2025c. Unified reward model for multimodal understanding and generation. arXiv preprint arXiv:2503.05236. — [arXiv:2503.05236](https://arxiv.org/abs/2503.05236) find
  70. Haoning Wu, Zicheng Zhang, Erli Zhang, Chaofeng Chen, Liang Liao, Annan Wang, Chunyi Li, Wenxiu Sun, Qiong Yan, Guangtao Zhai, and 1 others. 2024. Q-bench: A benchmark for general-purpose foundation models on low-level vision. In ICLR. find
  71. Shijie Xia, Xuefeng Li, Yixin Liu, Tongshuang Wu, and Pengfei Liu. 2025. Evaluating mathematical reasoning beyond accuracy. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 27723–27730.
  72. Kun Xiang, Zhili Liu, Zihao Jiang, Yunshuang Nie, Runhui Huang, Haoxiang Fan, Hanhui Li, Weiran Huang, Yihan Zeng, Jianhua Han, and 1 others. 2024. Atomthink: A slow thinking framework for multimodal mathematical reasoning. arXiv preprint arXiv:2411.11930. — [arXiv:2411.11930](https://arxiv.org/abs/2411.11930) find
  73. Guowei Xu, Peng Jin, Hao Li, Yibing Song, Lichao Sun, and Li Yuan. 2024. Llava-cot: Let vision language models reason step-by-step. CoRR. find
  74. Le Yang, Ziwei Zheng, Boxu Chen, Zhengyu Zhao, Chenhao Lin, and Chao Shen. 2025a. 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
  75. Tianyun Yang, Ziniu Li, Juan Cao, and Chang Xu. 2025b. Understanding and mitigating hallucination in large vision-language models via modular attribution and intervention. In The Thirteenth International Conference on Learning Representations. find
  76. 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
  77. 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
  78. Qifan Yu, Juncheng Li, Longhui Wei, Liang Pang, Wentao Ye, Bosheng Qin, Siliang Tang, Qi Tian, and Yueting Zhuang. 2024. Hallucidoctor: Mitigating hallucinatory toxicity in visual instruction data. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12944– 129… find
  79. Xiang Yue, Yuansheng Ni, Kai Zhang, Tianyu Zheng, Ruoqi Liu, Ge Zhang, Samuel Stevens, Dongfu Jiang, Weiming Ren, Yuxuan Sun, and 1 others. 2024a. Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi. In Proceedings of the IEEE/CVF Conference on Computer V…
  80. Zihao Yue, Liang Zhang, and Qin Jin. 2024b. Less is more: Mitigating multimodal hallucination from an eos decision perspective. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 11766– 11781. find
  81. Huaxiu Yao. 2024. Analyzing and mitigating object hallucination in large vision-language models. In The Twelfth International Conference on Learning Representations. find
  82. Xin Zou, Yizhou Wang, Yibo Yan, Yuanhuiyi Lyu, Kening Zheng, Sirui Huang, Junkai Chen, Peijie Jiang, Jia Liu, Chang Tang, and 1 others. 2024. Look twice before you answer: Memory-space visual retracing for hallucination mitigation in multimodal large language models. In Forty-second International Co… find
  83. Bohan Zhai, Shijia Yang, Xiangchen Zhao, Chenfeng Xu, Sheng Shen, Dongdi Zhao, Kurt Keutzer, Manling Li, Tan Yan, and Xiangjun Fan. 2023. Halle-switch: Rethinking and controlling object existence hallucinations in large vision-language models for detailed caption. find
  84. Jinrui Zhang, Teng Wang, Haigang Zhang, Ping Lu, and Feng Zheng. 2024a. Reflective instruction tuning: Mitigating hallucinations in large vision-language models. In European Conference on Computer Vision, pages 196–213. Springer. find
  85. Ruiyang Zhang, Hu Zhang, and Zhedong Zheng. 2024b. Vl-uncertainty: Detecting hallucination in large vision-language model via uncertainty estimation. arXiv preprint arXiv:2411.11919. — [arXiv:2411.11919](https://arxiv.org/abs/2411.11919) find
  86. Ruohong Zhang, Bowen Zhang, Yanghao Li, Haotian Zhang, Zhiqing Sun, Zhe Gan, Yinfei Yang, Ruoming Pang, and Yiming Yang. 2024c. Improve vision language model chain-of-thought reasoning. arXiv preprint arXiv:2410.16198.
  87. Yudong Zhang, Ruobing Xie, Xingwu Sun, Yiqing Huang, Jiansheng Chen, Zhanhui Kang, Di Wang, and Yu Wang. 2024d. Dhcp: Detecting hallucinations by cross-modal attention pattern in large vision-language models. arXiv preprint arXiv:2411.18659. — [arXiv:2411.18659](https://arxiv.org/abs/2411.18659) find
  88. Yunhang Shen Yulei Qin Mengdan Zhang, Xu Lin Jinrui Yang Xiawu Zheng, Ke Li Xing Sun Yunsheng Wu, Rongrong Ji Chaoyou Fu, and Peixian Chen. 2021. Mme: A comprehensive evaluation benchmark for multimodal large language models. arXiv preprint arXiv:2306.13394.
  89. Fei Zhao, Chengcui Zhang, Runlin Zhang, Tianyang Wang, and Xi Li. 2025. Mitigating image captioning hallucinations in vision-language models. arXiv preprint arXiv:2505.03420. — [arXiv:2505.03420](https://arxiv.org/abs/2505.03420) find
  90. Zhiyuan Zhao, Bin Wang, Linke Ouyang, Xiaoyi Dong, Jiaqi Wang, and Conghui He. 2023. Beyond hallucinations: Enhancing lvlms through hallucination-aware direct preference optimization. arXiv preprint arXiv:2311.16839. — [arXiv:2311.16839](https://arxiv.org/abs/2311.16839) find
  91. Yiyang Zhou, Chenhang Cui, Jaehong Yoon, Linjun Zhang, Zhun Deng, Chelsea Finn, Mohit Bansal, and find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/uppaal-2026-journey-before-destination-importance-visual/