---
title: "DICA — paper by Yang et al. (2026) — summary and ideas"
description: "Multimodal large language models often hallucinate in visual question answering. 51 references."
authors: ["Hao Yang", "Jin Wang", "Xuejie Zhang"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.1933/"
doi: "10.18653/v1/2026.findings-acl.1933"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/yang-2026-dica-dual-indicator-guided-contrastive/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yang-2026-dica-dual-indicator-guided-contrastive/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/29/) / DICA: Dual-Indicator Guided Contrastive Alignment in Multimodal Large Language Models

# DICA: Dual-Indicator Guided Contrastive Alignment in Multimodal Large Language Models

**Authors:** [Hao Yang](https://md.research.elamur.ai/free/en/authors/hao-yang/), [Jin Wang](https://md.research.elamur.ai/free/en/authors/jin-wang/) and [Xuejie Zhang](https://md.research.elamur.ai/free/en/authors/xuejie-zhang/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.1933/) · [PDF](https://aclanthology.org/2026.findings-acl.1933.pdf) · [DOI 10.18653/v1/2026.findings-acl.1933](https://doi.org/10.18653/v1/2026.findings-acl.1933) · [OpenAlex](https://openalex.org/W7166861132)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Multimodal large language models often hallucinate in visual question answering. The authors attribute this to two distinct failures. In attention drift, focus on visual tokens suddenly scatters to irrelevant regions. In underuse of visual evidence, the output stops depending on the image and falls back on language priors. Analysing LLaVA-1.5 layer by layer, they find that healthy reasoning narrows attention from global to local and keeps image reliance high. Errors tend to follow spikes or dips in two indicators. Visual Attention Entropy (VAE) is Shannon entropy over attention to image tokens. Output–Image Correlation (OIC) is a KL-style divergence between output distributions computed with and without the image. DICA is a training-free decoding method that tracks both signals at every layer and step and applies a targeted correction when a threshold is crossed. VAE-GDC calibrates hidden states using a neutral query, and OIC-GGR recalibrates predictions with the best alternative distribution. On POPE, CHAIR and MME, DICA generally beats contrastive-decoding baselines. It works without retraining or architectural changes and diagnoses which failure is occurring.

## Key points
- The method has two modules, VAE-Guided Drift Correction (VAE-GDC) and OIC-Guided Grounding Restoration (OIC-GGR). Each is triggered when its indicator exceeds a fraction of its dynamic range. The authors tested it on LLaVA-v1.5 and Qwen-VL.
- On CHAIR with LLaVA-v1.5, DICA scores CHAIR_s 41.8 and CHAIR_i 11.5. The strongest baseline (MoD) scores 42.6 and 12.4, and plain sampling scores 52.8 and 15.9.
- On MME, total scores reach 661.5 for LLaVA-v1.5 (MoD: 638.3) and 648.3 for Qwen-VL (MoD: 613.3). On the POPE Count subset, DICA is slightly below the best baseline.
- On POPE, DICA fixes 37.4% of initially wrong answers and flips only about 1.3% of correct ones to wrong. VAE-GDC fires more often than OIC-GGR, mostly in deeper layers, and removing it hurts performance most in ablations.
- Limitations include added decoding latency, manually tuned fixed thresholds, and no ability to fix blind spots of the base encoder or LLM. Code is at github.com/BGWH123/DICA.

*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

- [Yunnan University](https://md.research.elamur.ai/free/en/universities/yunnan-university/) — University, Kunming, China · 20 works · 40 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works

🧭 Topics (2): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,894 works · [🖼️ Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/) · 811 works

## Cite

Cite as: Hao Yang, Jin Wang and Xuejie Zhang. 2026. DICA: Dual-Indicator Guided Contrastive Alignment in Multimodal Large Language Models. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{yang2026dica,
  title = {{DICA: Dual-Indicator Guided Contrastive Alignment in Multimodal Large Language Models}},
  author = {Hao Yang, Jin Wang and Xuejie Zhang},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1933},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1933}
}
```

- [← previous DialogueSidon: Recovering Full-Duplex Dialogue Tracks from In-the-Wild Dialogue Audio](https://md.research.elamur.ai/free/en/papers/nakata-2026-dialoguesidon-recovering-full-duplex-dialogue/)
- [next → Did You Forget What I Asked? Prospective Memory Failures in Large Language Models](https://md.research.elamur.ai/free/en/papers/mittal-2026-did-you-forget-what-i/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/29/)

## References

51 references, 25 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023. [Qwen-vl: A versatile vision-language model for understanding, localization, and reasoning](https://md.research.elamur.ai/free/en/papers/bai-2023-qwen-vl-versatile-vision-language/). arXiv preprint arXiv:2308.12966.
2. Yong Jae Lee. 2024. Vip-llava: Making large multimodal models understand arbitrary visual prompts. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12914– 12923. [find](https://scholar.google.com/scholar?q=Yong+Jae+Lee%2E+2024%2E+Vip%2Dllava%3A+Making+large+multimodal+models+understand+arbitrary+visual+prompts%2E+In+Proceedings+of+the+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern+Recognition%2C+pages+12914%E2%80%93+12)
3. Xinlong Chen, Yuanxing Zhang, Qiang Liu, Junfei Wu, Fuzheng Zhang, and Tieniu Tan. 2025. Mixture of decoding: An attention-inspired adaptive decoding strategy to mitigate hallucinations in large vision-language models. arXiv preprint arXiv:2505.17061. [find](https://scholar.google.com/scholar?q=Xinlong+Chen%2C+Yuanxing+Zhang%2C+Qiang+Liu%2C+Junfei+Wu%2C+Fuzheng+Zhang%2C+and+Tieniu+Tan%2E+2025%2E+Mixture+of+decoding%3A+An+attention%2Dinspired+adaptive+decoding+strategy+to+mitigate+hallucinations+in+large+visio)
4. 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](https://md.research.elamur.ai/free/en/papers/chuang-2023-dola-decoding-contrasting-layers-improves/). arXiv preprint arXiv:2309.03883.
5. 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](https://md.research.elamur.ai/free/en/papers/dai-2023-instructblip-towards-general-purpose-vision/). Advances in neural information processing systems, 36:49250–49267.
6. Abhishek Das, Harsh Agrawal, Larry Zitnick, Devi Parikh, and Dhruv Batra. 2017. Human attention in visual question answering: Do humans and deep networks look at the same regions? Computer Vision and Image Understanding, 163:90–100. [find](https://scholar.google.com/scholar?q=Abhishek+Das%2C+Harsh+Agrawal%2C+Larry+Zitnick%2C+Devi+Parikh%2C+and+Dhruv+Batra%2E+2017%2E+Human+attention+in+visual+question+answering%3A+Do+humans+and+deep+networks+look+at+the+same+regions%3F+Computer+Vision+and+)
7. 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](https://scholar.google.com/scholar?q=Alessandro+Favero%2C+Luca+Zancato%2C+Matthew+Trager%2C+Siddharth+Choudhary%2C+Pramuditha+Perera%2C+Alessandro+Achille%2C+Ashwin+Swaminathan%2C+and+Stefano+Soatto%2E+2024%2E+Multi%2Dmodal+hallucination+control+by+visual+i)
8. 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](https://md.research.elamur.ai/free/en/papers/huang-2023-opera-alleviating-hallucination-multi-modal/). In Proceedings of the IEEE/CVF Conference on Computer Vis…
9. Drew A Hudson and Christopher D Manning. 2019. [Gqa: A new dataset for real-world visual reasoning and compositional question answering](https://md.research.elamur.ai/free/en/papers/hudson-2019-gqa-new-dataset-real-world/). In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 6700–6709.
10. Laurent Itti and Christof Koch. 2001. Computational modelling of visual attention. Nature reviews neuroscience, 2(3):194–203. [find](https://scholar.google.com/scholar?q=Laurent+Itti+and+Christof+Koch%2E+2001%2E+Computational+modelling+of+visual+attention%2E+Nature+reviews+neuroscience%2C+2%283%29%3A194%E2%80%93203%2E)
11. Ali Furkan Biten, Lluís Gómez, and Dimosthenis Karatzas. 2022. Let there be a clock on the beach: Reducing object hallucination in image captioning. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 1381–1390. [find](https://scholar.google.com/scholar?q=Ali+Furkan+Biten%2C+Llu%C3%ADs+G%C3%B3mez%2C+and+Dimosthenis+Karatzas%2E+2022%2E+Let+there+be+a+clock+on+the+beach%3A+Reducing+object+hallucination+in+image+captioning%2E+In+Proceedings+of+the+IEEE%2FCVF+Winter+Conference+on)
12. 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](https://md.research.elamur.ai/free/en/papers/ji-2022-survey-hallucination-natural-language-generation/). ACM computing surveys, 55(12):1–38.
13. Mu Cai, Haotian Liu, Siva Karthik Mustikovela, Gregory P Meyer, Yuning Chai, Dennis Park, and Taehyeon Kim, Joonkee Kim, Gihun Lee, and Se-Young Yun. 2023. Instructive decoding: Instruction-tuned large language models are self-refiner from noisy instructions. arXiv preprint arXiv:2311.00233. — [arXiv:2311.00233](https://arxiv.org/abs/2311.00233) [find](https://scholar.google.com/scholar?q=Mu+Cai%2C+Haotian+Liu%2C+Siva+Karthik+Mustikovela%2C+Gregory+P+Meyer%2C+Yuning+Chai%2C+Dennis+Park%2C+and+Taehyeon+Kim%2C+Joonkee+Kim%2C+Gihun+Lee%2C+and+Se%2DYoung+Yun%2E+2023%2E+Instructive+decoding%3A+Instruction%2Dtuned+larg)
14. Solomon Kullback and Richard A. Leibler. 1951. On information and sufficiency. The Annals of Mathematical Statistics, 22(1):79–86. [find](https://scholar.google.com/scholar?q=Solomon+Kullback+and+Richard+A%2E+Leibler%2E+1951%2E+On+information+and+sufficiency%2E+The+Annals+of+Mathematical+Statistics%2C+22%281%29%3A79%E2%80%9386%2E)
15. 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](https://md.research.elamur.ai/free/en/papers/leng-2023-mitigating-object-hallucinations-large-vision/). In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13872–13…
16. Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023a. [Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models](https://md.research.elamur.ai/free/en/papers/li-2023-blip-2-bootstrapping-language-image/). In International conference on machine learning, pages 19730–19742. PMLR.
17. Xiang Lisa Li, Ari Holtzman, Daniel Fried, Percy Liang, Jason Eisner, Tatsunori B Hashimoto, Luke Zettlemoyer, and Mike Lewis. 2023b. [Contrastive decoding: Open-ended text generation as optimization](https://md.research.elamur.ai/free/en/papers/li-2022-contrastive-decoding-open-ended-text/). In Proceedings of the 61st annual meeting of the association for computational linguistics (volume 1…
18. Yifan Li, Yifan Du, Kun Zhou, Jinpeng Wang, Wayne Xin Zhao, and Ji-Rong Wen. 2023c. [Evaluating object hallucination in large vision-language models](https://md.research.elamur.ai/free/en/papers/li-2023-evaluating-object-hallucination-large-vision/). arXiv preprint arXiv:2305.10355.
19. Yifan Li, Yifan Du, Kun Zhou, Jinpeng Wang, Xin Zhao, and Ji-Rong Wen. 2023d. [Evaluating object hallucination in large vision-language models](https://md.research.elamur.ai/free/en/papers/li-2023-evaluating-object-hallucination-large-vision/). In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 292–305, Singapore. Association for Computational Linguistic…
20. J. Lin. 1991. Divergence measures based on the shannon entropy. IEEE Transactions on Information Theory, 37(1):145–151. [find](https://scholar.google.com/scholar?q=J%2E+Lin%2E+1991%2E+Divergence+measures+based+on+the+shannon+entropy%2E+IEEE+Transactions+on+Information+Theory%2C+37%281%29%3A145%E2%80%93151%2E)
21. Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C. Lawrence Zitnick. 2014. [Microsoft COCO: Common objects in context](https://md.research.elamur.ai/free/en/papers/lin-2014-microsoft-coco-common-objects-context/). In Computer Vision – ECCV 2014, pages 740–755. Springer International Publishing.
22. Fang Liu, Yang Liu, Lin Shi, Houkun Huang, Ruifeng Wang, Zhen Yang, Li Zhang, Zhongqi Li, and Yuchi Ma. 2024a. Exploring and evaluating hallucinations in llm-powered code generation. arXiv preprint arXiv:2404.00971. — [arXiv:2404.00971](https://arxiv.org/abs/2404.00971) [find](https://scholar.google.com/scholar?q=Fang+Liu%2C+Yang+Liu%2C+Lin+Shi%2C+Houkun+Huang%2C+Ruifeng+Wang%2C+Zhen+Yang%2C+Li+Zhang%2C+Zhongqi+Li%2C+and+Yuchi+Ma%2E+2024a%2E+Exploring+and+evaluating+hallucinations+in+llm%2Dpowered+code+generation%2E+arXiv+preprint+ar)
23. Fuxiao Liu, Kevin Lin, Linjie Li, Jianfeng Wang, Yaser Yacoob, and Lijuan Wang. 2023a. [Mitigating hallucination in large multi-modal models via robust instruction tuning](https://md.research.elamur.ai/free/en/papers/liu-2023-mitigating-hallucination-large-multi-modal/). arXiv preprint arXiv:2306.14565.
24. Haotian Liu, Chunyuan Li, Yuheng Li, and Yong Jae Lee. 2024b. [Improved baselines with visual instruction tuning](https://md.research.elamur.ai/free/en/papers/liu-2023-improved-baselines-visual-instruction-tuning/). In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 26296–26306.
25. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023b. [Visual instruction tuning](https://md.research.elamur.ai/free/en/papers/liu-2023-visual-instruction-tuning/). Advances in neural information processing systems, 36:34892– 34916.
26. Kuanghong Liu, Jin Wang, Kangjian He, Dan Xu, and Xuejie Zhang. 2025a. Vision-aware multimodal prompt tuning for uploadable multi-source few-shot domain adaptation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 18897–18905. [find](https://scholar.google.com/scholar?q=Kuanghong+Liu%2C+Jin+Wang%2C+Kangjian+He%2C+Dan+Xu%2C+and+Xuejie+Zhang%2E+2025a%2E+Vision%2Daware+multimodal+prompt+tuning+for+uploadable+multi%2Dsource+few%2Dshot+domain+adaptation%2E+In+Proceedings+of+the+AAAI+Conferen)
27. Qiang Liu, Xinlong Chen, Yue Ding, Bowen Song, Weiqiang Wang, Shu Wu, and Liang Wang. 2025b. Attention-guided self-reflection for zero-shot hallucination detection in large language models. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 21016– 21032. [find](https://scholar.google.com/scholar?q=Qiang+Liu%2C+Xinlong+Chen%2C+Yue+Ding%2C+Bowen+Song%2C+Weiqiang+Wang%2C+Shu+Wu%2C+and+Liang+Wang%2E+2025b%2E+Attention%2Dguided+self%2Dreflection+for+zero%2Dshot+hallucination+detection+in+large+language+models%2E+In+Proceed)
28. David Navon. 1977. Forest before trees: The precedence of global features in visual perception. Cognitive Psychology, 9(3):353–383. [find](https://scholar.google.com/scholar?q=David+Navon%2E+1977%2E+Forest+before+trees%3A+The+precedence+of+global+features+in+visual+perception%2E+Cognitive+Psychology%2C+9%283%29%3A353%E2%80%93383%2E)
29. Clement Neo, Shay B Cohen, and Fazl Barez. 2024. Interpreting context look-ups in transformers: Investigating attention-mlp interactions, 2024. URL https://arxiv.org/abs/2402.15055, page 25. [↗](https://arxiv.org/abs/2402.15055)
30. Zhiliang Peng, Wenhui Wang, Li Dong, Yaru Hao, Shaohan Huang, Shuming Ma, and Furu Wei. 2023. [Kosmos-2: Grounding multimodal large language models to the world](https://md.research.elamur.ai/free/en/papers/peng-2023-kosmos-2-grounding-multimodal-large/). arXiv preprint arXiv:2306.14824.
31. Anna Rohrbach, Lisa Anne Hendricks, Kaylee Burns, Trevor Darrell, and Kate Saenko. 2018. [Object hallucination in image captioning](https://md.research.elamur.ai/free/en/papers/rohrbach-2018-object-hallucination-image-captioning/). In Proc. EMNLP, pages 4035–4045. Association for Computational Linguistics.
32. Dustin Schwenk, Apoorv Khandelwal, Christopher Clark, Kenneth Marino, and Roozbeh Mottaghi. 2022. [A-okvqa: A benchmark for visual question answering using world knowledge](https://md.research.elamur.ai/free/en/papers/schwenk-2022-okvqa-benchmark-visual-question-answering/). In European conference on computer vision, pages 146–162. Springer.
33. C. E. Shannon. 1948. A mathematical theory of communication. The Bell System Technical Journal, 27(3):379–423. [find](https://scholar.google.com/scholar?q=C%2E+E%2E+Shannon%2E+1948%2E+A+mathematical+theory+of+communication%2E+The+Bell+System+Technical+Journal%2C+27%283%29%3A379%E2%80%93423%2E)
34. Zhiqing Sun, Sheng Shen, Shengcao Cao, Haotian Liu, Chunyuan Li, Yikang Shen, Chuang Gan, Liangyan Gui, Yu-Xiong Wang, Yiming Yang, and 1 others. 2024. [Aligning large multimodal models with factually augmented rlhf](https://md.research.elamur.ai/free/en/papers/sun-2023-aligning-large-multimodal-models-factually/). In Findings of the Association for Computational Linguistics: ACL 2024, pages 13088–…
35. 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](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-open-efficient-foundation-language/). arXiv preprint arXiv:2302.13971.
36. Andrés Villa, Juan León Alcázar, Motasem Alfarra, Vladimir Araujo, Alvaro Soto, and Bernard Ghanem. 2025. Eagle: Enhanced visual grounding minimizes hallucinations in instructional multimodal models. arXiv preprint arXiv:2501.02699. — [arXiv:2501.02699](https://arxiv.org/abs/2501.02699) [find](https://scholar.google.com/scholar?q=Andr%C3%A9s+Villa%2C+Juan+Le%C3%B3n+Alc%C3%A1zar%2C+Motasem+Alfarra%2C+Vladimir+Araujo%2C+Alvaro+Soto%2C+and+Bernard+Ghanem%2E+2025%2E+Eagle%3A+Enhanced+visual+grounding+minimizes+hallucinations+in+instructional+multimodal+models%2E+)
37. Lei Wang, Jiabang He, Shenshen Li, Ning Liu, and Ee-Peng Lim. 2024. Mitigating fine-grained hallucination by fine-tuning large vision-language models with caption rewrites. In International Conference on Multimedia Modeling, pages 32–45. Springer. [find](https://scholar.google.com/scholar?q=Lei+Wang%2C+Jiabang+He%2C+Shenshen+Li%2C+Ning+Liu%2C+and+Ee%2DPeng+Lim%2E+2024%2E+Mitigating+fine%2Dgrained+hallucination+by+fine%2Dtuning+large+vision%2Dlanguage+models+with+caption+rewrites%2E+In+International+Conference)
38. 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 Findings of the Association for Computational Linguistics: ACL 2025, pages 1927–1951. [find](https://scholar.google.com/scholar?q=Sangmin+Woo%2C+Donguk+Kim%2C+Jaehyuk+Jang%2C+Yubin+Choi%2C+and+Changick+Kim%2E+2025%2E+Don%E2%80%99t+miss+the+forest+for+the+trees%3A+Attentional+vision+calibration+for+large+vision+language+models%2E+In+Findings+of+the+Asso)
39. Xinhao Xu, Hui Chen, Mengyao Lyu, Sicheng Zhao, Yizhe Xiong, Zijia Lin, Jungong Han, and Guiguang Ding. 2025. Mitigating hallucinations in multi-modal large language models via image token attention-guided decoding. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the… [find](https://scholar.google.com/scholar?q=Xinhao+Xu%2C+Hui+Chen%2C+Mengyao+Lyu%2C+Sicheng+Zhao%2C+Yizhe+Xiong%2C+Zijia+Lin%2C+Jungong+Han%2C+and+Guiguang+Ding%2E+2025%2E+Mitigating+hallucinations+in+multi%2Dmodal+large+language+models+via+image+token+attention%2Dg)
40. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, and 41 others. 2025a. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). Preprint, arXiv:2505.09388.
41. Hao Yang, Jin Wang, and Xuejie Zhang. 2025b. Evl-mcot: Enhanced vision-language multi-cot for harmful meme detection. In CCF International Conference on Natural Language Processing and Chinese Computing, pages 403–415. Springer. [find](https://scholar.google.com/scholar?q=Hao+Yang%2C+Jin+Wang%2C+and+Xuejie+Zhang%2E+2025b%2E+Evl%2Dmcot%3A+Enhanced+vision%2Dlanguage+multi%2Dcot+for+harmful+meme+detection%2E+In+CCF+International+Conference+on+Natural+Language+Processing+and+Chinese+Computi)
42. Li Yuan, Qingfei Huang, Bingshan Zhu, Yi Cai, Qingbao Huang, Changmeng Zheng, Zikun Deng, and Tao Wang. 2026. Hybrid-dmkg: A hybrid reasoning framework over dynamic multimodal knowledge graphs for multimodal multihop qa with knowledge editing. In Proceedings of the AAAI Conference on Artificial Inte… [find](https://scholar.google.com/scholar?q=Li+Yuan%2C+Qingfei+Huang%2C+Bingshan+Zhu%2C+Yi+Cai%2C+Qingbao+Huang%2C+Changmeng+Zheng%2C+Zikun+Deng%2C+and+Tao+Wang%2E+2026%2E+Hybrid%2Ddmkg%3A+A+hybrid+reasoning+framework+over+dynamic+multimodal+knowledge+graphs+for+mul)
43. 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](https://md.research.elamur.ai/free/en/papers/fu-2023-mme-comprehensive-evaluation-benchmark-multimodal/). arXiv preprint arXiv:2306.13394, 18:2.
44. Guangmin Zheng, Jun Kong, Jin Wang, and Xuejie Zhang. 2025. Enhanced multimodal chain-of-thought with visual self-contrastive distillation. In 2025 IEEE International Conference on Multimedia and Expo (ICME), pages 1–6. IEEE. [find](https://scholar.google.com/scholar?q=Guangmin+Zheng%2C+Jun+Kong%2C+Jin+Wang%2C+and+Xuejie+Zhang%2E+2025%2E+Enhanced+multimodal+chain%2Dof%2Dthought+with+visual+self%2Dcontrastive+distillation%2E+In+2025+IEEE+International+Conference+on+Multimedia+and+Expo)
45. Guangmin Zheng, Jin Wang, Xiaobing Zhou, and Xuejie Zhang. 2024. Enhancing semantics in multimodal chain of thought via soft negative sampling. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 6059– 60… [find](https://scholar.google.com/scholar?q=Guangmin+Zheng%2C+Jin+Wang%2C+Xiaobing+Zhou%2C+and+Xuejie+Zhang%2E+2024%2E+Enhancing+semantics+in+multimodal+chain+of+thought+via+soft+negative+sampling%2E+In+Proceedings+of+the+2024+Joint+International+Conferenc)
46. 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](https://md.research.elamur.ai/free/en/papers/zhou-2023-analyzing-mitigating-object-hallucination-large/). arXiv preprint arXiv:2310.00754.
47. Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2023. [Minigpt-4: Enhancing vision-language understanding with advanced large language models](https://md.research.elamur.ai/free/en/papers/zhu-2023-minigpt-4-enhancing-vision-language/). arXiv preprint arXiv:2304.10592.
48. Jia-Yu Yao, Kun-Peng Ning, Zhen-Hui Liu, Mu-Nan Ning, Yu-Yang Liu, and Li Yuan. 2023. Llm lies: Hallucinations are not bugs, but features as adversarial examples. arXiv preprint arXiv:2310.01469. — [arXiv:2310.01469](https://arxiv.org/abs/2310.01469) [find](https://scholar.google.com/scholar?q=Jia%2DYu+Yao%2C+Kun%2DPeng+Ning%2C+Zhen%2DHui+Liu%2C+Mu%2DNan+Ning%2C+Yu%2DYang+Liu%2C+and+Li+Yuan%2E+2023%2E+Llm+lies%3A+Hallucinations+are+not+bugs%2C+but+features+as+adversarial+examples%2E+arXiv+preprint+arXiv%3A2310%2E01469%2E+%E2%80%94+%5Ba)
49. Alfred L Yarbus. 2013. Eye movements and vision. Springer. [find](https://scholar.google.com/scholar?q=Alfred+L+Yarbus%2E+2013%2E+Eye+movements+and+vision%2E+Springer%2E)
50. Tianyu Yu, Yuan Yao, Haoye Zhang, Taiwen He, Yifeng Han, Ganqu Cui, Jinyi Hu, Zhiyuan Liu, Hai-Tao Zheng, Maosong Sun, and 1 others. 2024. [Rlhf-v: Towards trustworthy mllms via behavior alignment from fine-grained correctional human feedback](https://md.research.elamur.ai/free/en/papers/yu-2023-rlhf-v-towards-trustworthy-mllms/). In Proceedings of the IEEE/CVF Conference on Computer Vis…
51. Li Yuan, Yi Cai, Xudong Shen, Qing Li, Qingbao Huang, Zikun Deng, and Tao Wang. 2025. Collaborative multi-lora experts with achievement-based multi-tasks loss for unified multimodal information extraction. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence,… [find](https://scholar.google.com/scholar?q=Li+Yuan%2C+Yi+Cai%2C+Xudong+Shen%2C+Qing+Li%2C+Qingbao+Huang%2C+Zikun+Deng%2C+and+Tao+Wang%2E+2025%2E+Collaborative+multi%2Dlora+experts+with+achievement%2Dbased+multi%2Dtasks+loss+for+unified+multimodal+information+extrac)

*Updated 2 November 2026*