---
title: "Once Correct, Still Wrong — paper by Mousi et al. (2026)"
description: "The authors build M2CQA, a benchmark of Creative Commons web images from 17 MENA countries. 44 references, cited by 2 papers here."
authors: ["Basel Mousi", "Fahim Dalvi", "Shammur Absar Chowdhury", "Firoj Alam", "Nadir Durrani"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.234/"
doi: "10.18653/v1/2026.findings-acl.234"
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/mousi-2026-once-correct-still-wrong-counterfactual/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/mousi-2026-once-correct-still-wrong-counterfactual/)

[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/8/) / Once Correct, Still Wrong: Counterfactual Hallucination in Multilingual Vision-Language Models

# Once Correct, Still Wrong: Counterfactual Hallucination in Multilingual Vision-Language Models

**Authors:** [Basel Mousi](https://md.research.elamur.ai/free/en/authors/basel-mousi/), [Fahim Dalvi](https://md.research.elamur.ai/free/en/authors/fahim-dalvi/), [Shammur Absar Chowdhury](https://md.research.elamur.ai/free/en/authors/shammur-absar-chowdhury/), [Firoj Alam](https://md.research.elamur.ai/free/en/authors/firoj-alam/) and [Nadir Durrani](https://md.research.elamur.ai/free/en/authors/nadir-durrani/) · **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.234/) · [PDF](https://aclanthology.org/2026.findings-acl.234.pdf) · [DOI 10.18653/v1/2026.findings-acl.234](https://doi.org/10.18653/v1/2026.findings-acl.234) · [OpenAlex](https://openalex.org/W7166879513)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [2](https://md.research.elamur.ai/free/en/papers/mousi-2026-once-correct-still-wrong-counterfactual/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Vision-language models can score well on accuracy and still endorse descriptions that sound culturally right but do not match the image. Existing hallucination benchmarks seldom probe this, especially for non-Western imagery and languages other than English. The authors build M2CQA, a benchmark of Creative Commons web images from 17 MENA countries. Each image comes with one true statement and two plausible counterfactuals in English, MSA, Egyptian and Levantine Arabic. They also propose CFHR, a metric that counts how often a model accepts a counterfactual among cases where it already judged the true statement correctly. This separates grounding failures from simple lack of knowledge. Testing Qwen3-VL, Gemma-3-VL, Fanar-Oryx and AIN with three prompting styles, they find that CFHR grows from English to MSA and grows further in dialects, even when accuracy stays high. Prompts that ask the model to reason before answering make hallucination worse, while answering first and justifying afterwards helps. The work shows that aggregate accuracy can hide culturally driven errors, and that dialectal Arabic is a weak spot.

## Key points
- **Dataset construction:**
  - Images were retrieved with geo-targeted Google Custom Search queries built on a taxonomy of 12 top-level categories.
  - GPT-4.1 produced MCQs, which were then turned into one Q+ and two Q− statements.
  - Items that both GPT-4.1 and Gemini-2.5-Flash answered correctly without seeing the image were discarded.
- **Translation:** MSA versions come from the Fanar Shaheen MT system, and the dialectal versions were produced with GPT-4.1.
- **Human verification:**
  - Annotators checked a stratified 15% sample.
  - Agreement on Need-Image was very high (AC1 ≈ 0.996).
  - Agreement on Q-Correctness was moderate (AC1 ≈ 0.741, raw ≈ 0.775).
- **Model findings:**
  - Qwen3-VL shows lower CFHR than Gemma-3-VL.
  - Fanar rejects more statements overall, which lowers both CFHR and Q+ accuracy.
  - AIN keeps Q+ accuracy high but has very high CFHR.
  - Larger models generally reduce CFHR, but the effect depends on the model family.
- **Release:** The dataset is available at huggingface.co/datasets/QCRI/M2CQA. It does not cover Gulf, Maghrebi or Iraqi dialects.

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

📚 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 (3): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,894 works · [🌍 Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · 882 works · [🖼️ Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/) · 811 works

## Cite

Cite as: Basel Mousi, Fahim Dalvi, Shammur Absar Chowdhury, Firoj Alam and Nadir Durrani. 2026. Once Correct, Still Wrong: Counterfactual Hallucination in Multilingual Vision-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{mousi2026once,
  title = {{Once Correct, Still Wrong: Counterfactual Hallucination in Multilingual Vision-Language Models}},
  author = {Basel Mousi, Fahim Dalvi, Shammur Absar Chowdhury, Firoj Alam and Nadir Durrani},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.234},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.234}
}
```

- [← previous On-Policy Self-Distillation for Efficient Diffusion Language Models with Early-Stage Calibration](https://md.research.elamur.ai/free/en/papers/zhu-2026-policy-self-distillation-efficient-diffusion/)
- [next → One Refiner to Unlock Them All: Inference-Time Reasoning Elicitation via Reinforcement Query Refinement](https://md.research.elamur.ai/free/en/papers/zhou-2026-one-refiner-unlock-them-all/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/8/)

## References

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

1. Shahad Al-Khalifa, Nadir Durrani, Hend Al-Khalifa, and Firoj Alam. 2025. [The landscape of arabic large language models (allms): A new era for arabic language technology](https://md.research.elamur.ai/free/en/papers/al-khalifa-2025-landscape-arabic-large-language-models/). Communications of the ACM. Online First. Firoj Alam, Abul Hasnat, Fatema Ahmad, Md.
2. Arid Hasan, and Maram Hasanain. 2024. [ArMeme: Propagandistic content in Arabic memes](https://md.research.elamur.ai/free/en/papers/alam-2024-armeme-propagandistic-content-arabic-memes/). In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 21071–21090, Miami, Florida, USA. Association for Computational Linguistics. Firoj Alam, Ali Ezzat Shahroor, Md.
3. Arid Hasan, Zien Sheikh Ali, Hunzalah Hassan Bhatti, Mohamed Bayan Kmainasi, Shammur Absar Chowdhury, Basel Mousi, Fahim Dalvi, Nadir Durrani, and Natasa Milic-Frayling. 2025. [EverydayM-MQA: A multilingual and multimodal framework for culturally grounded spoken visual qa](https://md.research.elamur.ai/free/en/papers/alam-2025-oasis-multilingual-multimodal-dataset-culturally/). Preprint, arXiv:2510.06371. [↗](https://arxiv.org/abs/2510.06371)
4. Fakhraddin Alwajih, Gagan Bhatia, and Muhammad Abdul-Mageed. 2024. [Dallah: A dialect-aware multimodal large language model for Arabic](https://md.research.elamur.ai/free/en/papers/alwajih-2024-dallah-dialect-aware-multimodal-large/). In Proceedings of the Second Arabic Natural Language Processing Conference, pages 320–336, Bangkok, Thailand. Association for Computational Linguistics. Fakhraddin Alwajih, Abdellah El Mekki, Samar Mohamed Magdy, AbdelRahim A. Elmadany, Omer Nacar, El Moatez Billah Nagoudi, Reem Abdel-Salam, Hanin Atwany, Youssef Nafea, Abdulfattah Mohammed Yahya, Rahaf Alhamouri, Hamzah A.
5. Alsayadi, Hiba Zayed, Sara Shatnawi, Serry Sibaee, Yasir Ech-chammakhy, Walid Al-Dhabyani, Marwa Mohamed Ali, Imen Jarraya, and 25 others. 2025. [Palm: A culturally inclusive and linguistically diverse dataset for Arabic LLMs](https://md.research.elamur.ai/free/en/papers/alwajih-2025-palm-culturally-inclusive-linguistically-diverse/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 32871–32894, Vienna, Austria. Association for Computational Linguistics.
6. Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, and 1 others. 2023. [Qwen technical report](https://md.research.elamur.ai/free/en/papers/bai-2023-qwen-technical-report/). arXiv preprint arXiv:2309.16609. [↗](https://arxiv.org/abs/2309.16609)
7. Shuai Bai, Yuxuan Cai, Ruizhe Chen, Keqin Chen, Xionghui Chen, Zesen Cheng, Lianghao Deng, Wei Ding, Chang Gao, Chunjiang Ge, Wenbin Ge, Zhifang Guo, Qidong Huang, Jie Huang, Fei Huang, Binyuan Hui, Shutong Jiang, Zhaohai Li, Mingsheng Li, and 45 others. 2025. [Qwen3-vl technical report](https://md.research.elamur.ai/free/en/papers/bai-2025-qwen3-vl-technical-report/). arXiv preprint arXiv:2511.21631. [↗](https://arxiv.org/abs/2511.21631)
8. Assaf Ben-Kish, Moran Yanuka, Morris Alper, Raja Giryes, and Hadar Averbuch-Elor. 2024. Mitigating open-vocabulary caption hallucinations. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 22680–22698, Miami, Florida, USA. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Assaf+Ben%2DKish%2C+Moran+Yanuka%2C+Morris+Alper%2C+Raja+Giryes%2C+and+Hadar+Averbuch%2DElor%2E+2024%2E+Mitigating+open%2Dvocabulary+caption+hallucinations%2E+In+Proceedings+of+the+2024+Conference+on+Empirical+Methods+in)
9. Houda Bouamor, Nizar Habash, Mohammad Salameh, Wajdi Zaghouani, Owen Rambow, Dana Abdulrahim, Ossama Obeid, Salam Khalifa, Fadhl Eryani, Alexander Erdmann, and Kemal Oflazer. 2018. The MADAR Arabic dialect corpus and lexicon. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan. European Language Resources Association (ELRA). [find](https://scholar.google.com/scholar?q=Houda+Bouamor%2C+Nizar+Habash%2C+Mohammad+Salameh%2C+Wajdi+Zaghouani%2C+Owen+Rambow%2C+Dana+Abdulrahim%2C+Ossama+Obeid%2C+Salam+Khalifa%2C+Fadhl+Eryani%2C+Alexander+Erdmann%2C+and+Kemal+Oflazer%2E+2018%2E+The+MADAR+Arabic+di)
10. Qingxing Cao, Junhao Cheng, Xiaodan Liang, and Liang Lin. 2024. VisDiaHalBench: A visual dialogue benchmark for diagnosing hallucination in large vision-language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12161–12176, Bangkok, Thailand. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Qingxing+Cao%2C+Junhao+Cheng%2C+Xiaodan+Liang%2C+and+Liang+Lin%2E+2024%2E+VisDiaHalBench%3A+A+visual+dialogue+benchmark+for+diagnosing+hallucination+in+large+vision%2Dlanguage+models%2E+In+Proceedings+of+the+62nd+Ann)
11. Jiawei Chen, Dingkang Yang, Tong Wu, Yue Jiang, Xiaolu Hou, Mingcheng Li, Shunli Wang, Dongling Xiao, Ke Li, and Lihua Zhang. 2024a. Detecting and evaluating medical hallucinations in large vision language models. Preprint, arXiv:2406.10185. [↗](https://arxiv.org/abs/2406.10185)
12. Xuweiyi Chen, Ziqiao Ma, Xuejun Zhang, Sihan Xu, Shengyi Qian, Jianing Yang, David F. Fouhey, and Joyce Chai. 2024b. Multi-object hallucination in vision language models. In Proceedings of the 38th International Conference on Neural Information Processing Systems, NIPS ’24, Red Hook, NY, USA. Curran Associates Inc. [find](https://scholar.google.com/scholar?q=Xuweiyi+Chen%2C+Ziqiao+Ma%2C+Xuejun+Zhang%2C+Sihan+Xu%2C+Shengyi+Qian%2C+Jianing+Yang%2C+David+F%2E+Fouhey%2C+and+Joyce+Chai%2E+2024b%2E+Multi%2Dobject+hallucination+in+vision+language+models%2E+In+Proceedings+of+the+38th+In)
13. Zhiyang Chen, Yousong Zhu, Yufei Zhan, Zhaowen Li, Chaoyang Zhao, Jinqiao Wang, and Ming Tang. 2023. Mitigating hallucination in visual language models with visual supervision. Preprint, arXiv:2311.16479. [↗](https://arxiv.org/abs/2311.16479)
14. Zhiyuan Chen, Yuecong Min, Jie Zhang, Bei Yan, Jiahao Wang, Xiaozhen Wang, and Shiguang Shan. 2025. A survey of multimodal hallucination evaluation and detection. Preprint, arXiv:2507.19024. [↗](https://arxiv.org/abs/2507.19024)
15. Fanar-Team, Ummar Abbas, Mohammad Shahmeer Ahmad, Firoj Alam, Enes Altinisik, Ehsannedin Asgari, Yazan Boshmaf, Sabri Boughorbel, Sanjay Chawla, Shammur Chowdhury, Fahim Dalvi, Kareem Darwish, Nadir Durrani, Mohamed Elfeky, Ahmed Elmagarmid, Mohamed Eltabakh, Masoomali Fatehkia, Anastasios Fragkopoulos, Maram Hasanain, and 23 others. 2025. [Fanar: An Arabic-centric multimodal generative AI platform](https://md.research.elamur.ai/free/en/papers/abbas-2025-fanar-arabic-centric-multimodal-generative/). https://arxiv.org/abs/ 2501.13944. [↗](https://arxiv.org/abs/)
16. Chaoyou Fu, Peixian Chen, Yunhang Shen, Yulei Qin, Mengdan Zhang, Xu Lin, Jinrui Yang, Xiawu Zheng, Ke Li, Xing Sun, and 1 others. 2023. [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. [↗](https://arxiv.org/abs/2306.13394)
17. Kilem Li Gwet. 2008. Computing inter-rater reliability and its variance in the presence of high agreement. British Journal of Mathematical and Statistical Psychology, 61(1):29–48. [find](https://scholar.google.com/scholar?q=Kilem+Li+Gwet%2E+2008%2E+Computing+inter%2Drater+reliability+and+its+variance+in+the+presence+of+high+agreement%2E+British+Journal+of+Mathematical+and+Statistical+Psychology%2C+61%281%29%3A29%E2%80%9348%2E)
18. Ahmed Heakl, Sara Ghaboura, Omkar Thawkar, Fahad Shahbaz Khan, Hisham Cholakkal, Rao Muhammad Anwer, and Salman Khan. 2025a. [AIN: The arabic inclusive large multimodal model](https://md.research.elamur.ai/free/en/papers/heakl-2025-ain-arabic-inclusive-large-multimodal/). arXiv preprint arXiv:2502.00094. [↗](https://arxiv.org/abs/2502.00094)
19. Ahmed Heakl, Sara Ghaboura, Omkar Thawkar, Fahad Shahbaz Khan, Hisham Cholakkal, Rao Muhammad Anwer, and Salman Khan. 2025b. [Ain: The arabic inclusive large multimodal model](https://md.research.elamur.ai/free/en/papers/heakl-2025-ain-arabic-inclusive-large-multimodal/). Preprint, arXiv:2502.00094. [↗](https://arxiv.org/abs/2502.00094)
20. Andrew Lampinen, Ishita Dasgupta, Stephanie Chan, Kory Mathewson, Mh Tessler, Antonia Creswell, James McClelland, Jane Wang, and Felix Hill. 2022. [Can language models learn from explanations in context?](https://md.research.elamur.ai/free/en/papers/lampinen-2022-can-language-models-learn-explanations/) In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 537–563, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
21. Li Li, Jiashu Qu, Linxin Song, Yuxiao Zhou, Yuehan Qin, Tiankai Yang, and Yue Zhao. 2025. Treble counterfactual VLMs: A causal approach to hallucination. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 18423–18434, Suzhou, China. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Li+Li%2C+Jiashu+Qu%2C+Linxin+Song%2C+Yuxiao+Zhou%2C+Yuehan+Qin%2C+Tiankai+Yang%2C+and+Yue+Zhao%2E+2025%2E+Treble+counterfactual+VLMs%3A+A+causal+approach+to+hallucination%2E+In+Findings+of+the+Association+for+Computation)
22. Yifan Li, Yifan Du, Kun Zhou, Jinpeng Wang, 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/). In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 292–305, Singapore. Association for Computational Linguistics.
23. 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, Cham. Springer International Publishing.
24. Hanchao Liu, Wenyuan Xue, Yifei Chen, Dapeng Chen, Xiutian Zhao, Ke Wang, Liping Hou, Rongjun Li, and Wei Peng. 2024. [A survey on hallucination in large vision-language models](https://md.research.elamur.ai/free/en/papers/liu-2024-survey-hallucination-large-vision-language/). arXiv preprint arXiv:2402.00253. [↗](https://arxiv.org/abs/2402.00253)
25. Jiazhen Liu, Yuhan Fu, Ruobing Xie, Runquan Xie, Xingwu Sun, Fengzong Lian, Zhanhui Kang, and Xirong Li. 2025. Phd: A chatgpt-prompted visual hallucination evaluation dataset. In CVPR. [find](https://scholar.google.com/scholar?q=Jiazhen+Liu%2C+Yuhan+Fu%2C+Ruobing+Xie%2C+Runquan+Xie%2C+Xingwu+Sun%2C+Fengzong+Lian%2C+Zhanhui+Kang%2C+and+Xirong+Li%2E+2025%2E+Phd%3A+A+chatgpt%2Dprompted+visual+hallucination+evaluation+dataset%2E+In+CVPR%2E)
26. Wen Huang, Hongbin Liu, Minxin Guo, and Neil Gong. 2024. Visual hallucinations of multi-modal large language models. In Findings of the Association for Computational Linguistics: ACL 2024, pages 9614–9631, Bangkok, Thailand. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Wen+Huang%2C+Hongbin+Liu%2C+Minxin+Guo%2C+and+Neil+Gong%2E+2024%2E+Visual+hallucinations+of+multi%2Dmodal+large+language+models%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+ACL+2024%2C+pages+9614%E2%80%93)
27. Holy Lovenia, Wenliang Dai, Samuel Cahyawijaya, Ziwei Ji, and Pascale Fung. 2024. Negative object presence evaluation (NOPE) to measure object hallucination in vision-language models. In Proceedings of the 3rd Workshop on Advances in Language and Vision Research (ALVR), pages 37–58, Bangkok, Thailand. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Holy+Lovenia%2C+Wenliang+Dai%2C+Samuel+Cahyawijaya%2C+Ziwei+Ji%2C+and+Pascale+Fung%2E+2024%2E+Negative+object+presence+evaluation+%28NOPE%29+to+measure+object+hallucination+in+vision%2Dlanguage+models%2E+In+Proceedings+o)
28. Chaoya Jiang, Hongrui Jia, Mengfan Dong, Wei Ye, Haiyang Xu, Ming Yan, Ji Zhang, and Shikun Zhang. 2024. Hal-eval: A universal and fine-grained hallucination evaluation framework for large vision language models. In Proceedings of the 32nd ACM International Conference on Multimedia, MM ’24, page 525534, New York, NY, USA. Association for Computing Machinery. Basel Mousi, Nadir Durrani, Fatema Ahmad, Md. [find](https://scholar.google.com/scholar?q=Chaoya+Jiang%2C+Hongrui+Jia%2C+Mengfan+Dong%2C+Wei+Ye%2C+Haiyang+Xu%2C+Ming+Yan%2C+Ji+Zhang%2C+and+Shikun+Zhang%2E+2024%2E+Hal%2Deval%3A+A+universal+and+fine%2Dgrained+hallucination+evaluation+framework+for+large+vision+lang)
29. Arid Hasan, Maram Hasanain, Tameem Kabbani, Fahim Dalvi, Shammur Absar Chowdhury, and Firoj Alam. 2025. [AraDiCE: Benchmarks for dialectal and cultural capabilities in LLMs](https://md.research.elamur.ai/free/en/papers/mousi-2025-aradice-benchmarks-dialectal-cultural-capabilities/). In Proceedings of the 31st International Conference on Computational Linguistics, pages 4186–4218, Abu Dhabi, UAE. Association for Computational Linguistics.
30. Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. [Large language models are zero-shot reasoners](https://md.research.elamur.ai/free/en/papers/kojima-2022-large-language-models-zero-shot/). In ICML 2022 Workshop on Knowledge Retrieval and Language Models.
31. Han Qiu, Jiaxing Huang, Peng Gao, Qin Qi, Xiaoqin Zhang, Ling Shao, and Shijian Lu. 2024. Longhalqa: Long-context hallucination evaluation for multimodal large language models. Preprint, arXiv:2410.09962. [↗](https://arxiv.org/abs/2410.09962)
32. 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 Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4035–4045, Brussels, Belgium. Association for Computational Linguistics.
33. David Romero, Chenyang Lyu, Haryo Akbarianto Wibowo, Teresa Lynn, Injy Hamed, Aditya Nanda Kishore, Aishik Mandal, Alina Dragonetti, Artem Abzaliev, Atnafu Lambebo Tonja, Bontu Fufa Balcha, Chenxi Whitehouse, Christian Salamea, Dan John Velasco, David Ifeoluwa Adelani, David Le Meur, Emilio Villa-Cueva, Fajri Koto, Fauzan Farooqui, and 57 others. 2024. [Cvqa: Culturally-diverse multilingual visual question answering benchmark](https://md.research.elamur.ai/free/en/papers/romero-2024-cvqa-culturally-diverse-multilingual-visual/). In Advances in Neural Information Processing Systems, volume 37, pages 11479–11505. Curran Associates, Inc.
34. Fanar Team, Ummar Abbas, Mohammad Shahmeer Ahmad, Minhaj Ahmad, Abdulaziz Al-Homaid, Anas Al-Nuaimi, Enes Altinisik, Ehsaneddin Asgari, Sanjay Chawla, Shammur Chowdhury, Fahim Dalvi, Kareem Darwish, Nadir Durrani, Mohamed Elfeky, Ahmed Elmagarmid, Mohamed Eltabakh, Asim Ersoy, Masoomali Fatehkia, Mohammed Qusay Hashim, and 18 others. 2026. [Fanar 2.0: Arabic generative ai stack](https://md.research.elamur.ai/free/en/papers/team-2026-fanar-2-0-arabic-generative/). Preprint, arXiv:2603.16397. [↗](https://arxiv.org/abs/2603.16397)
35. Gemma Team, Aishwarya Kamath, Johan Ferret, Shreya Pathak, Nino Vieillard, Ramona Merhej, Sarah Perrin, Tatiana Matejovicova, Alexandre Ramé, Morgane Rivière, and 1 others. 2025a. Gemma 3 technical report. arXiv preprint arXiv:2503.19786. [↗](https://arxiv.org/abs/2503.19786)
36. Lei Wang, Jiabang He, Shenshen Li, Ning Liu, and Ee-Peng Lim. 2023. Mitigating fine-grained hallucination by fine-tuning large vision-language models with caption rewrites. Preprint, arXiv:2312.01701. [↗](https://arxiv.org/abs/2312.01701)
37. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. 2022. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). In Proceedings of the 36th International Conference on Neural Information Processing Systems, NIPS ’22, Red Hook, NY, USA. Curran Associates Inc.
38. Mingrui Wu, Jiayi Ji, Oucheng Huang, Jiale Li, Yuhang Wu, Xiaoshuai Sun, and Rongrong Ji. 2024a. Evaluating and analyzing relationship hallucinations in large vision-language models. In Proceedings of the 41st International Conference on Machine Learning, ICML’24. JMLR.org. [find](https://scholar.google.com/scholar?q=Mingrui+Wu%2C+Jiayi+Ji%2C+Oucheng+Huang%2C+Jiale+Li%2C+Yuhang+Wu%2C+Xiaoshuai+Sun%2C+and+Rongrong+Ji%2E+2024a%2E+Evaluating+and+analyzing+relationship+hallucinations+in+large+vision%2Dlanguage+models%2E+In+Proceedings+of)
39. Xiyang Wu, Tianrui Guan, Dianqi Li, Shuaiyi Huang, Xiaoyu Liu, Xijun Wang, Ruiqi Xian, Abhinav Shrivastava, Furong Huang, Jordan Lee Boyd-Graber, Tianyi Zhou, and Dinesh Manocha. 2024b. AutoHallusion: Automatic generation of hallucination benchmarks for vision-language models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 8395–8419, Miami, Florida, USA. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Xiyang+Wu%2C+Tianrui+Guan%2C+Dianqi+Li%2C+Shuaiyi+Huang%2C+Xiaoyu+Liu%2C+Xijun+Wang%2C+Ruiqi+Xian%2C+Abhinav+Shrivastava%2C+Furong+Huang%2C+Jordan+Lee+Boyd%2DGraber%2C+Tianyi+Zhou%2C+and+Dinesh+Manocha%2E+2024b%2E+AutoHallusion%3A)
40. Bohan Zhai, Shijia Yang, Chenfeng Xu, Sheng Shen, Kurt Keutzer, Chunyuan Li, and Manling Li. 2024. Halle-control: Controlling object hallucination in large multimodal models. Preprint, arXiv:2310.01779. [↗](https://arxiv.org/abs/2310.01779)
41. Gemma Team, Aishwarya Kamath, Johan Ferret, Shreya Pathak, Nino Vieillard, Ramona Merhej, Sarah Perrin, Tatiana Matejovicova, Alexandre Ramé, Morgane Rivière, Louis Rouillard, Thomas Mesnard, Geoffrey Cideron, Jean bastien Grill, Sabela Ramos, Edouard Yvinec, Michelle Casbon, Etienne Pot, Ivo Penchev, and 197 others. 2025b. Gemma 3 technical report. Preprint, arXiv:2503.19786. [↗](https://arxiv.org/abs/2503.19786)
42. Yahan Tu, Rui Hu, and Jitao Sang. 2025. Ode: Open-set evaluation of hallucinations in multimodal large language models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 19836–19845. [find](https://scholar.google.com/scholar?q=Yahan+Tu%2C+Rui+Hu%2C+and+Jitao+Sang%2E+2025%2E+Ode%3A+Open%2Dset+evaluation+of+hallucinations+in+multimodal+large+language+models%2E+In+Proceedings+of+the+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern+Recogni)
43. Andrés Villa, Juan Léon, Alvaro Soto, and Bernard Ghanem. 2025. Behind the magic, merlim: Multi-modal evaluation benchmark for large image-language models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pages 492–502. [find](https://scholar.google.com/scholar?q=Andr%C3%A9s+Villa%2C+Juan+L%C3%A9on%2C+Alvaro+Soto%2C+and+Bernard+Ghanem%2E+2025%2E+Behind+the+magic%2C+merlim%3A+Multi%2Dmodal+evaluation+benchmark+for+large+image%2Dlanguage+models%2E+In+Proceedings+of+the+IEEE%2FCVF+Conference+on)
44. Junyang Wang, Yuhang Wang, Guohai Xu, Jing Zhang, Yukai Gu, Haitao Jia, Jiaqi Wang, Haiyang Xu, Ming Yan, Ji Zhang, and Jitao Sang. 2024. [Amber: An llm-free multi-dimensional benchmark for mllms hallucination evaluation](https://md.research.elamur.ai/free/en/papers/wang-2023-amber-llm-free-multi-dimensional/). Preprint, arXiv:2311.07397. [↗](https://arxiv.org/abs/2311.07397)

*Updated 2 November 2026*