---
title: "Cracking the Code of Hallucination in LVLMs with Vision-aware"
description: "The authors define Vision-aware Head Divergence (VHD), which measures how much each attention… 32 references, cited by 13 papers here."
authors: ["Jinghan He", "Kuan Zhu", "Haiyun Guo", "Junfeng Fang", "Zhenglin Hua", "Yuheng Jia", "Ming Tang", "Tat-Seng Chua", "Jinqiao Wang"]
year: 2025
venue: "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2025.acl-long.175/"
doi: "10.18653/v1/2025.acl-long.175"
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/he-2025-cracking-code-hallucination-lvlms-vision/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/he-2025-cracking-code-hallucination-lvlms-vision/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/4/) / Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence

# Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence

**Authors:** Jinghan He, Kuan Zhu, Haiyun Guo, [Junfeng Fang](https://md.research.elamur.ai/free/en/authors/junfeng-fang/), Zhenglin Hua, [Yuheng Jia](https://md.research.elamur.ai/free/en/authors/yuheng-jia/), Ming Tang, [Tat-Seng Chua](https://md.research.elamur.ai/free/en/authors/tat-seng-chua/) and Jinqiao Wang · **Year:** 2025 · **Venue:** [Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2025](https://md.research.elamur.ai/free/en/venues/acl/2025/)) · **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/2025.acl-long.175/) · [PDF](https://aclanthology.org/2025.acl-long.175.pdf) · [DOI 10.18653/v1/2025.acl-long.175](https://doi.org/10.18653/v1/2025.acl-long.175) · [OpenAlex](https://openalex.org/W4412886703)

**Citations:** 8 citations (OpenAlex, 2026-10-14) · [13](https://md.research.elamur.ai/free/en/papers/he-2025-cracking-code-hallucination-lvlms-vision/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Large vision-language models (LVLMs) often hallucinate, describing objects that are not in the image. Most existing remedies retrain the model or adjust output logits after generation. This paper instead looks inside the multi-head attention module. The authors define Vision-aware Head Divergence (VHD), which measures how much each attention head's output changes when the image is removed from the input. Only a small number of heads react strongly to visual context. The VHD values of the top heads in each layer are combined into a per-token score, Token-VHD (T-VHD).

On a sample of CHAIR images, hallucinated words and sentences tend to have lower T-VHD. This supports the view that over-reliance on language priors drives hallucination. Building on this, the authors propose Vision-aware Head Reinforcement (VHR), a training-free method that finds vision-sensitive heads using VHD and amplifies their outputs during decoding. On standard hallucination benchmarks, VHR beats state-of-the-art decoding strategies with almost no added inference time. This makes it a cheap, interpretable fix that works from the model's internal states.

## Key points
- VHD is the Euclidean distance between a head's output with and without image tokens at a given generation step. In LLaVA-1.5, only a few heads score high and most are nearly insensitive.
- T-VHD sums the top-k VHD scores per layer across layers. Taking only the top k keeps insensitive heads from diluting the signal.
- An analysis of 500 random CHAIR images showed that hallucinated objects and sentences cluster at lower T-VHD values.
- VHR scales up the outputs of the selected heads. The best results come from reinforcing about the last 14 layers; reinforcing more layers hurts output quality.
- The only overhead is one extra image-free forward pass at the first generation step. Code is available at github.com/jinghan1he/VHR.

*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

- [National University of Singapore](https://md.research.elamur.ai/free/en/universities/national-university-of-singapore/) — University, Singapore, Singapore · 180 works · 34,304 citations
- [Chinese Academy of Sciences](https://md.research.elamur.ai/free/en/government/chinese-academy-of-sciences/) — Government body, Beijing, China · 194 works · 23,906 citations
- [Institute of Automation](https://md.research.elamur.ai/free/en/labs/institute-of-automation/) — Research institute, Beijing, China · 70 works · 14,251 citations
- [University of Chinese Academy of Sciences](https://md.research.elamur.ai/free/en/universities/university-of-chinese-academy-of-sciences/) — University, Beijing, China · 147 works · 8,480 citations
- [Southeast University](https://md.research.elamur.ai/free/en/universities/southeast-university-cn/) — University, Nanjing, China · 28 works · 354 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works

## Cite

Cite as: 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. Proceedings of the 63rd 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.

```bibtex
@inproceedings{he2025cracking,
  title = {{Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence}},
  author = {Jinghan He, Kuan Zhu, Haiyun Guo, Junfeng Fang, Zhenglin Hua, Yuheng Jia, Ming Tang, Tat-Seng Chua and Jinqiao Wang},
  booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2025},
  doi = {10.18653/v1/2025.acl-long.175},
  url = {https://doi.org/10.18653/v1/2025.acl-long.175}
}
```

- [← previous CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models](https://md.research.elamur.ai/free/en/papers/li-2025-codetree-agent-guided-tree-search/)
- [next → Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models](https://md.research.elamur.ai/free/en/papers/qiu-2025-demons-detail-implementing-load-balancing/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/4/)

## References

32 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Liang Chen, Haozhe Zhao, Tianyu Liu, Shuai Bai, Junyang Lin, Chang Zhou, and Baobao Chang. 2025. [An image is worth 1/2 tokens after layer 2: Plug-and-play inference acceleration for large vision-language models](https://md.research.elamur.ai/free/en/papers/chen-2024-image-worth-1-2-tokens/). In European Conference on Computer Vision, pages 19–35. Springer.
2. 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.
3. Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale 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/). Preprint, arXiv:2305.06500.
4. Junfeng Fang, Zac Bi, Ruipeng Wang, Houcheng Jiang, Yuan Gao, Kun Wang, An Zhang, Jie Shi, Xiang Wang, and Tat-Seng Chua. 2024a. Towards neuron attributions in multi-modal large language models. Advances in Neural Information Processing Systems, 37:122867–122890. [find](https://scholar.google.com/scholar?q=Junfeng+Fang%2C+Zac+Bi%2C+Ruipeng+Wang%2C+Houcheng+Jiang%2C+Yuan+Gao%2C+Kun+Wang%2C+An+Zhang%2C+Jie+Shi%2C+Xiang+Wang%2C+and+Tat%2DSeng+Chua%2E+2024a%2E+Towards+neuron+attributions+in+multi%2Dmodal+large+language+models%2E+Advan)
5. Junfeng Fang, Houcheng Jiang, Kun Wang, Yunshan Ma, Shi Jie, Xiang Wang, Xiangnan He, and Tat-Seng Chua. 2024b. Alphaedit: Null-space constrained knowledge editing for language models. arXiv preprint arXiv:2410.02355. [find](https://scholar.google.com/scholar?q=Junfeng+Fang%2C+Houcheng+Jiang%2C+Kun+Wang%2C+Yunshan+Ma%2C+Shi+Jie%2C+Xiang+Wang%2C+Xiangnan+He%2C+and+Tat%2DSeng+Chua%2E+2024b%2E+Alphaedit%3A+Null%2Dspace+constrained+knowledge+editing+for+language+models%2E+arXiv+preprint+)
6. 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. arXiv preprint arXiv:2405.15683. — [arXiv:2405.15683](https://arxiv.org/abs/2405.15683) [find](https://scholar.google.com/scholar?q=Sreyan+Ghosh%2C+Chandra+Kiran+Reddy+Evuru%2C+Sonal+Kumar%2C+Utkarsh+Tyagi%2C+Oriol+Nieto%2C+Zeyu+Jin%2C+and+Dinesh+Manocha%2E+2024%2E+Visual+description+grounding+reduces+hallucinations+and+boosts+reasoning+in+lvlms%2E)
7. Xuan Gong, Tianshi Ming, Xinpeng Wang, and Zhihua Wei. 2024. Damro: Dive into the attention mechanism of lvlm to reduce object hallucination. arXiv preprint arXiv:2410.04514. [find](https://scholar.google.com/scholar?q=Xuan+Gong%2C+Tianshi+Ming%2C+Xinpeng+Wang%2C+and+Zhihua+Wei%2E+2024%2E+Damro%3A+Dive+into+the+attention+mechanism+of+lvlm+to+reduce+object+hallucination%2E+arXiv+preprint+arXiv%3A2410%2E04514%2E)
8. Yash Goyal, Tejas Khot, Douglas Summers-Stay, Dhruv Batra, and Devi Parikh. 2017. [Making the v in vqa matter: Elevating the role of image understanding in visual question answering](https://md.research.elamur.ai/free/en/papers/goyal-2016-making-v-vqa-matter-elevating/). In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 6904–6913.
9. Jinghan He, Haiyun Guo, Kuan Zhu, Zihan Zhao, Ming Tang, and Jinqiao Wang. 2024. Seekr: Selective attention-guided knowledge retention for continual learning of large language models. arXiv preprint arXiv:2411.06171. [find](https://scholar.google.com/scholar?q=Jinghan+He%2C+Haiyun+Guo%2C+Kuan+Zhu%2C+Zihan+Zhao%2C+Ming+Tang%2C+and+Jinqiao+Wang%2E+2024%2E+Seekr%3A+Selective+attention%2Dguided+knowledge+retention+for+continual+learning+of+large+language+models%2E+arXiv+preprint+a)
10. 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](https://scholar.google.com/scholar?q=Qidong+Huang%2C+Xiaoyi+Dong%2C+Pan+Zhang%2C+Bin+Wang%2C+Conghui+He%2C+Jiaqi+Wang%2C+Dahua+Lin%2C+Weiming+Zhang%2C+and+Nenghai+Yu%2E+2024%2E+Opera%3A+Alleviating+hallucination+in+multi%2Dmodal+large+language+models+via+over%2Dt)
11. Junho Kim, Hyunjun Kim, Yeonju Kim, and Yong Man Ro. 2024. Code: Contrasting self-generated description to combat hallucination in large multi-modal models. arXiv preprint arXiv:2406.01920. — [arXiv:2406.01920](https://arxiv.org/abs/2406.01920) [find](https://scholar.google.com/scholar?q=Junho+Kim%2C+Hyunjun+Kim%2C+Yeonju+Kim%2C+and+Yong+Man+Ro%2E+2024%2E+Code%3A+Contrasting+self%2Dgenerated+description+to+combat+hallucination+in+large+multi%2Dmodal+models%2E+arXiv+preprint+arXiv%3A2406%2E01920%2E+%E2%80%94+%5BarXiv%3A2)
12. 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…
13. Kenneth Li, Oam Patel, Fernanda Viégas, Hanspeter Pfister, and Martin Wattenberg. 2024. [Inference-time intervention: Eliciting truthful answers from a language model](https://md.research.elamur.ai/free/en/papers/li-2023-inference-time-intervention-eliciting-truthful/). Advances in Neural Information Processing Systems, 36.
14. Yifan Li, Yifan Du, Kun Zhou, Jinpeng Wang, Wayne Xin Zhao, and Ji-Rong Wen. 2023. [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.
15. 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: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pag…
16. Yulei Niu, Kaihua Tang, Hanwang Zhang, Zhiwu Lu, Xian-Sheng Hua, and Ji-Rong Wen. 2021. Counterfactual vqa: A cause-effect look at language bias. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 12700– 12710. [find](https://scholar.google.com/scholar?q=Yulei+Niu%2C+Kaihua+Tang%2C+Hanwang+Zhang%2C+Zhiwu+Lu%2C+Xian%2DSheng+Hua%2C+and+Ji%2DRong+Wen%2E+2021%2E+Counterfactual+vqa%3A+A+cause%2Deffect+look+at+language+bias%2E+In+Proceedings+of+the+IEEE%2FCVF+conference+on+computer+)
17. Letitia Parcalabescu and Anette Frank. 2024. Do vision & language decoders use images and text equally? how self-consistent are their explanations? arXiv preprint arXiv:2404.18624. — [arXiv:2404.18624](https://arxiv.org/abs/2404.18624) [find](https://scholar.google.com/scholar?q=Letitia+Parcalabescu+and+Anette+Frank%2E+2024%2E+Do+vision+%26+language+decoders+use+images+and+text+equally%3F+how+self%2Dconsistent+are+their+explanations%3F+arXiv+preprint+arXiv%3A2404%2E18624%2E+%E2%80%94+%5BarXiv%3A2404%2E18624)
18. 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/). arXiv preprint arXiv:1809.02156.
19. John Tabak. 2014. Geometry: the language of space and form. Infobase Publishing. [find](https://scholar.google.com/scholar?q=John+Tabak%2E+2014%2E+Geometry%3A+the+language+of+space+and+form%2E+Infobase+Publishing%2E)
20. 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 preprint arXiv:2310.16045. [find](https://scholar.google.com/scholar?q=Shukang+Yin%2C+Chaoyou+Fu%2C+Sirui+Zhao%2C+Tong+Xu%2C+Hao+Wang%2C+Dianbo+Sui%2C+Yunhang+Shen%2C+Ke+Li%2C+Xing+Sun%2C+and+Enhong+Chen%2E+2023%2E+Woodpecker%3A+Hallucination+correction+for+multimodal+large+language+models%2E+arX)
21. Junwei You, Haotian Shi, Zhuoyu Jiang, Zilin Huang, Rui Gan, Keshu Wu, Xi Cheng, Xiaopeng Li, and Bin Ran. 2024. V2x-vlm: End-to-end v2x cooperative autonomous driving through large vision-language models. arXiv preprint arXiv:2408.09251. — [arXiv:2408.09251](https://arxiv.org/abs/2408.09251) [find](https://scholar.google.com/scholar?q=Junwei+You%2C+Haotian+Shi%2C+Zhuoyu+Jiang%2C+Zilin+Huang%2C+Rui+Gan%2C+Keshu+Wu%2C+Xi+Cheng%2C+Xiaopeng+Li%2C+and+Bin+Ran%2E+2024%2E+V2x%2Dvlm%3A+End%2Dto%2Dend+v2x+cooperative+autonomous+driving+through+large+vision%2Dlanguage+mo)
22. Qinan Yu, Jack Merullo, and Ellie Pavlick. 2023. Characterizing mechanisms for factual recall in language models. arXiv preprint arXiv:2310.15910. [find](https://scholar.google.com/scholar?q=Qinan+Yu%2C+Jack+Merullo%2C+and+Ellie+Pavlick%2E+2023%2E+Characterizing+mechanisms+for+factual+recall+in+language+models%2E+arXiv+preprint+arXiv%3A2310%2E15910%2E)
23. Tianyu Yu, Yuan Yao, Haoye Zhang, Taiwen He, Yifeng Han, Ganqu Cui, Jinyi Hu, Zhiyuan Liu, Hai-Tao Zheng, Maosong Sun, et al. 2024. Rlhf-v: Towards trustworthy mllms via behavior alignment from fine-grained correctional human feedback. In Proceedings of the IEEE/CVF Conference on Computer Vision and… [find](https://scholar.google.com/scholar?q=Tianyu+Yu%2C+Yuan+Yao%2C+Haoye+Zhang%2C+Taiwen+He%2C+Yifeng+Han%2C+Ganqu+Cui%2C+Jinyi+Hu%2C+Zhiyuan+Liu%2C+Hai%2DTao+Zheng%2C+Maosong+Sun%2C+et+al%2E+2024%2E+Rlhf%2Dv%3A+Towards+trustworthy+mllms+via+behavior+alignment+from+fine%2Dg)
24. 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 preprint arXiv:2411.09968. — [arXiv:2411.09968](https://arxiv.org/abs/2411.09968) [find](https://scholar.google.com/scholar?q=Xiaofeng+Zhang%2C+Yihao+Quan%2C+Chaochen+Gu%2C+Chen+Shen%2C+Xiaosong+Yuan%2C+Shaotian+Yan%2C+Hao+Cheng%2C+Kaijie+Wu%2C+and+Jieping+Ye%2E+2024%2E+Seeing+clearly+by+layer+two%3A+Enhancing+attention+heads+to+alleviate+halluci)
25. Hanchao Liu, Wenyuan Xue, Yifei Chen, Dapeng Chen, Xiutian Zhao, Ke Wang, Liping Hou, Rongjun Li, and Wei Peng. 2024a. A survey on hallucination in large vision-language models. arXiv preprint arXiv:2402.00253. [find](https://scholar.google.com/scholar?q=Hanchao+Liu%2C+Wenyuan+Xue%2C+Yifei+Chen%2C+Dapeng+Chen%2C+Xiutian+Zhao%2C+Ke+Wang%2C+Liping+Hou%2C+Rongjun+Li%2C+and+Wei+Peng%2E+2024a%2E+A+survey+on+hallucination+in+large+vision%2Dlanguage+models%2E+arXiv+preprint+arXiv%3A2)
26. 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](https://scholar.google.com/scholar?q=Zhiyuan+Zhao%2C+Bin+Wang%2C+Linke+Ouyang%2C+Xiaoyi+Dong%2C+Jiaqi+Wang%2C+and+Conghui+He%2E+2023%2E+Beyond+hallucinations%3A+Enhancing+lvlms+through+hallucination%2Daware+direct+preference+optimization%2E+arXiv+preprint+a)
27. 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.
28. 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](https://scholar.google.com/scholar?q=Yiyang+Zhou%2C+Chenhang+Cui%2C+Jaehong+Yoon%2C+Linjun+Zhang%2C+Zhun+Deng%2C+Chelsea+Finn%2C+Mohit+Bansal%2C+and+Huaxiu+Yao%2E+2023%2E+Analyzing+and+mitigating+object+hallucination+in+large+vision%2Dlanguage+models%2E+arXiv)
29. Haotian Liu, Chunyuan Li, Yuheng Li, Bo Li, Yuanhan Zhang, Sheng Shen, and Yong Jae Lee. 2024c. Llava-next: Improved reasoning, ocr, and world knowledge. [find](https://scholar.google.com/scholar?q=Haotian+Liu%2C+Chunyuan+Li%2C+Yuheng+Li%2C+Bo+Li%2C+Yuanhan+Zhang%2C+Sheng+Shen%2C+and+Yong+Jae+Lee%2E+2024c%2E+Llava%2Dnext%3A+Improved+reasoning%2C+ocr%2C+and+world+knowledge%2E)
30. Zhenhong Zhou, Haiyang Yu, Xinghua Zhang, Rongwu Xu, Fei Huang, Kun Wang, Yang Liu, Junfeng Fang, and Yongbin Li. 2024. On the role of attention heads in large language model safety. arXiv preprint arXiv:2410.13708. — [arXiv:2410.13708](https://arxiv.org/abs/2410.13708) [find](https://scholar.google.com/scholar?q=Zhenhong+Zhou%2C+Haiyang+Yu%2C+Xinghua+Zhang%2C+Rongwu+Xu%2C+Fei+Huang%2C+Kun+Wang%2C+Yang+Liu%2C+Junfeng+Fang%2C+and+Yongbin+Li%2E+2024%2E+On+the+role+of+attention+heads+in+large+language+model+safety%2E+arXiv+preprint+ar)
31. 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 preprint arXiv:2402.18476. — [arXiv:2402.18476](https://arxiv.org/abs/2402.18476) [find](https://scholar.google.com/scholar?q=Lanyun+Zhu%2C+Deyi+Ji%2C+Tianrun+Chen%2C+Peng+Xu%2C+Jieping+Ye%2C+and+Jun+Liu%2E+2024%2E+Ibd%3A+Alleviating+hallucinations+in+large+vision%2Dlanguage+models+via+image%2Dbiased+decoding%2E+arXiv+preprint+arXiv%3A2402%2E18476%2E+%E2%80%94)
32. A a cup on the right side, and a bowl located near the center of the table. Additionally, there is a chair positioned on the left side of the table. [find](https://scholar.google.com/scholar?q=A+a+cup+on+the+right+side%2C+and+a+bowl+located+near+the+center+of+the+table%2E+Additionally%2C+there+is+a+chair+positioned+on+the+left+side+of+the+table%2E)

*Updated 31 October 2026*