---
title: "“So, How Much Do LLMs Hallucinate on Low-Resource"
description: "The paper examines how often large language models produce fabricated or unsupported answers… 32 references, cited by 1 paper here."
authors: ["Kushal Trivedi", "Murtuza Shaikh", "Sriyansh Sharma"]
year: 2026
venue: "Proceedings of the Second Workshop on Language Models for Low-Resource Languages (LoResLM 2026)"
source: "https://aclanthology.org/2026.loreslm-1.24/"
doi: "10.18653/v1/2026.loreslm-1.24"
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/trivedi-2026-so-how-much-do-llms/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/trivedi-2026-so-how-much-do-llms/)

[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/19/) / “So, How Much Do LLMs Hallucinate on Low-Resource Languages?” A Quantitative and Qualitative Analysis

# “So, How Much Do LLMs Hallucinate on Low-Resource Languages?” A Quantitative and Qualitative Analysis

**Authors:** Kushal Trivedi, Murtuza Shaikh and Sriyansh Sharma · **Year:** 2026 · **Venue:** [Proceedings of the Second Workshop on Language Models for Low-Resource Languages (LoResLM 2026)](https://md.research.elamur.ai/free/en/venues/loreslm/) ([Workshop on Language Models for Low-Resource Languages 2026](https://md.research.elamur.ai/free/en/venues/loreslm/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.loreslm-1.24/) · [PDF](https://aclanthology.org/2026.loreslm-1.24.pdf) · [DOI 10.18653/v1/2026.loreslm-1.24](https://doi.org/10.18653/v1/2026.loreslm-1.24) · [OpenAlex](https://openalex.org/W7140093312)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · 1 in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper examines how often large language models produce fabricated or unsupported answers when they respond to questions in low-resource languages, specifically Burmese and Armenian. Two experiments were run. In the first, Llama 3.1 8B/70B, Gemini 2.5 and the regional SeaLLM model answered Burmese medical questions about Mpox. Each model was tested with zero-shot, one-shot, three-shot and chain-of-thought few-shot prompts. In the second, Llama 3.1 70B, Gemini 2.5 and the Armenian HyGPT 10B answered SynDARin reading-comprehension items. The background paragraph and the answer options were removed step by step across three conditions. Outputs were scored with multilingual semantic similarity, an NLI-based hallucination rate, and human checks.

Removing context raised hallucination, most sharply for HyGPT 10B. Small monolingual models performed on par with much larger multilingual ones. However, the authors find that the automatic metrics are unreliable. NLI marks most answers as neutral, similarity and hallucination rate are only weakly related, and vague replies can make a model's score look better. The work shows that hallucination evaluation outside high-resource languages needs human review and more dedicated datasets.

## Key points
- **Data:**
  - Mpox-Myanmar: 99 Burmese question–answer pairs, all of them used.
  - SynDARin: about 1.2K Armenian items, each with a paragraph and four options. Only the first 50 test items were used because of API rate limits.
- **Metrics and settings:**
  - Similarity was computed with paraphrase-multilingual-MiniLM-L12-v2. Answers were labelled correct above 0.75, partially correct from 0.50, and hallucinated below 0.50. These thresholds were set empirically.
  - NLI used mDeBERTa-v3. The hallucination rate is the number of contradictions divided by all NLI judgments.
  - Temperature was 0.10 and the output limit was 1024 tokens.
- **Experiment 2, first condition (paragraph plus options):** Gemini 2.5 achieved the highest accuracy at 76.00%. Once options and context were removed, Llama 3.1 70B held up more consistently.
- **SeaLLM 1.5B:** It had a low factual hallucination rate, but 40–50% of its answers were generic. Its score improves because neutral NLI labels enlarge the denominator, not because its answers are more correct.
- **Language filtering:** A Burmese-character ratio was used to classify responses. Answers below 0.50 were treated as language failures and excluded from the similarity analysis.

*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 (4): [🖥️ 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

🧭 Topics (2): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works · [🌱 Low-resource languages](https://md.research.elamur.ai/free/en/topics/low-resource-languages/) · 267 works

## Cite

Cite as: Kushal Trivedi, Murtuza Shaikh and Sriyansh Sharma. 2026. “So, How Much Do LLMs Hallucinate on Low-Resource Languages?” A Quantitative and Qualitative Analysis. Proceedings of the Second Workshop on Language Models for Low-Resource Languages (LoResLM 2026).

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

```bibtex
@inproceedings{trivedi2026so,
  title = {{“So, How Much Do LLMs Hallucinate on Low-Resource Languages?” A Quantitative and Qualitative Analysis}},
  author = {Kushal Trivedi, Murtuza Shaikh and Sriyansh Sharma},
  booktitle = {Proceedings of the Second Workshop on Language Models for Low-Resource Languages (LoResLM 2026)},
  year = {2026},
  doi = {10.18653/v1/2026.loreslm-1.24},
  url = {https://doi.org/10.18653/v1/2026.loreslm-1.24}
}
```

- [← previous “Penny Wise, Pixel Foolish”: Bypassing Price Constraints in Multimodal Agents via Visual Adversarial Perturbations](https://md.research.elamur.ai/free/en/papers/qian-2026-penny-wise-pixel-foolish-bypassing/)
- [next → “We Are (Language) Family”: Adapting Transformer models to related minority languages with linguistic data](https://md.research.elamur.ai/free/en/papers/otal-2026-we-are-language-family-adapting/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/19/)

## References

32 references, 13 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Vibhor Agarwal, Yiqiao Jin, Mohit Chandra, Munmun De Choudhury, Srijan Kumar, and Nishanth Sastry. 2024. Medhalu: Hallucinations in responses to healthcare queries by large language models. arXiv preprint arXiv:2409.19492. — [arXiv:2409.19492](https://arxiv.org/abs/2409.19492) [find](https://scholar.google.com/scholar?q=Vibhor+Agarwal%2C+Yiqiao+Jin%2C+Mohit+Chandra%2C+Munmun+De+Choudhury%2C+Srijan+Kumar%2C+and+Nishanth+Sastry%2E+2024%2E+Medhalu%3A+Hallucinations+in+responses+to+healthcare+queries+by+large+language+models%2E+arXiv+prep)
2. Pawitsapak Akarajaradwong, Pirat Pothavorn, Chompakorn Chaksangchaichot, Panuthep Tasawong, Thitiwat Nopparatbundit, Keerakiat Pratai, and Sarana Nutanong. 2025. Nitibench: Benchmarking llm frameworks on thai legal question answering capabilities. In Proceedings of the 2025 Conference on Empirical M… [find](https://scholar.google.com/scholar?q=Pawitsapak+Akarajaradwong%2C+Pirat+Pothavorn%2C+Chompakorn+Chaksangchaichot%2C+Panuthep+Tasawong%2C+Thitiwat+Nopparatbundit%2C+Keerakiat+Pratai%2C+and+Sarana+Nutanong%2E+2025%2E+Nitibench%3A+Benchmarking+llm+frameworks)
3. Samuel Bowman, Gabor Angeli, Christopher Potts, and Christopher D Manning. 2015. [A large annotated corpus for learning natural language inference](https://md.research.elamur.ai/free/en/papers/bowman-2015-large-annotated-corpus-learning-natural/). In Proceedings of the 2015 conference on empirical methods in natural language processing, pages 632–642.
4. Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter,… — [Language Models are Few-Shot Learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/)
5. Meng Cao, Yue Dong, and Jackie Chi Kit Cheung. 2022. [Hallucinated but factual! inspecting the factuality of hallucinations in abstractive summarization](https://md.research.elamur.ai/free/en/papers/cao-2022-hallucinated-but-factual-inspecting-factuality/). In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3340–3354.
6. Haoyang Chen, Dian Kong, Xiangyuan Li, and Chongjun Wang. 2025. Multi-round q&a hallucination analysis of llms in geographical education. In Advanced Intelligent Computing Technology and Applications, pages 14–26, Singapore. Springer Nature Singapore. [find](https://scholar.google.com/scholar?q=Haoyang+Chen%2C+Dian+Kong%2C+Xiangyuan+Li%2C+and+Chongjun+Wang%2E+2025%2E+Multi%2Dround+q%26a+hallucination+analysis+of+llms+in+geographical+education%2E+In+Advanced+Intelligent+Computing+Technology+and+Applications%2C)
7. Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, and 1 others. 2025. [Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities](https://md.research.elamur.ai/free/en/papers/comanici-2025-gemini-2-5-pushing-frontier/). arX…
8. Souvik Das, Sougata Saha, and Rohini K Srihari. 2022. Diving deep into modes of fact hallucinations in dialogue systems. In Findings of the association for computational linguistics: EMNLP 2022, pages 684–699. [find](https://scholar.google.com/scholar?q=Souvik+Das%2C+Sougata+Saha%2C+and+Rohini+K+Srihari%2E+2022%2E+Diving+deep+into+modes+of+fact+hallucinations+in+dialogue+systems%2E+In+Findings+of+the+association+for+computational+linguistics%3A+EMNLP+2022%2C+pages)
9. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. [BERT: pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). CoRR, abs/1810.04805.
10. Gayane Ghazaryan, Erik Arakelyan, Isabelle Augenstein, and Pasquale Minervini. 2025. Syndarin: Synthesising datasets for automated reasoning in low-resource languages. In Proceedings of the 31st International Conference on Computational Linguistics, pages 6459–6466. [find](https://scholar.google.com/scholar?q=Gayane+Ghazaryan%2C+Erik+Arakelyan%2C+Isabelle+Augenstein%2C+and+Pasquale+Minervini%2E+2025%2E+Syndarin%3A+Synthesising+datasets+for+automated+reasoning+in+low%2Dresource+languages%2E+In+Proceedings+of+the+31st+Inter)
11. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, and 1 others. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv preprint arXiv:2407.21783.
12. Muhammad Usman Hadi, Rizwan Qureshi, Abbas Shah, Muhammad Irfan, Anas Zafar, Muhammad Bilal Shaikh, Naveed Akhtar, Jia Wu, Seyedali Mirjalili, and 1 others. 2023. A survey on large language models: Applications, challenges, limitations, and practical usage. Authorea Preprints. [find](https://scholar.google.com/scholar?q=Muhammad+Usman+Hadi%2C+Rizwan+Qureshi%2C+Abbas+Shah%2C+Muhammad+Irfan%2C+Anas+Zafar%2C+Muhammad+Bilal+Shaikh%2C+Naveed+Akhtar%2C+Jia+Wu%2C+Seyedali+Mirjalili%2C+and+1+others%2E+2023%2E+A+survey+on+large+language+models%3A+Ap)
13. Pengcheng He, Xiaodong Liu, Jianfeng Gao, and Weizhu Chen. 2021. [Deberta: Decoding-enhanced bert with disentangled attention](https://md.research.elamur.ai/free/en/papers/he-2020-deberta-decoding-enhanced-bert-disentangled/). In International Conference on Learning Representations.
14. Yue Jiang, Jiawei Chen, Dingkang Yang, Mingcheng Li, Shunli Wang, Tong Wu, Ke Li, and Lihua Zhang. 2025. Comt: Chain-of-medical-thought reduces hallucination in medical report generation. In ICASSP 2025 -2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1–… [find](https://scholar.google.com/scholar?q=Yue+Jiang%2C+Jiawei+Chen%2C+Dingkang+Yang%2C+Mingcheng+Li%2C+Shunli+Wang%2C+Tong+Wu%2C+Ke+Li%2C+and+Lihua+Zhang%2E+2025%2E+Comt%3A+Chain%2Dof%2Dmedical%2Dthought+reduces+hallucination+in+medical+report+generation%2E+In+ICASSP+20)
15. Yiqiao Jin, Mohit Chandra, Gaurav Verma, Yibo Hu, Munmun De Choudhury, and Srijan Kumar. 2024. Better to ask in english: Cross-lingual evaluation of large language models for healthcare queries. In Proceedings of the ACM Web Conference 2024, pages 2627–2638. [find](https://scholar.google.com/scholar?q=Yiqiao+Jin%2C+Mohit+Chandra%2C+Gaurav+Verma%2C+Yibo+Hu%2C+Munmun+De+Choudhury%2C+and+Srijan+Kumar%2E+2024%2E+Better+to+ask+in+english%3A+Cross%2Dlingual+evaluation+of+large+language+models+for+healthcare+queries%2E+In+Pr)
16. Haoqiang Kang and Xiao-Yang Liu. 2023. Deficiency of large language models in finance: An empirical examination of hallucination. Preprint, arXiv:2311.15548. — [arXiv:2311.15548](https://arxiv.org/abs/2311.15548) [find](https://scholar.google.com/scholar?q=Haoqiang+Kang+and+Xiao%2DYang+Liu%2E+2023%2E+Deficiency+of+large+language+models+in+finance%3A+An+empirical+examination+of+hallucination%2E+Preprint%2C+arXiv%3A2311%2E15548%2E+%E2%80%94+%5BarXiv%3A2311%2E15548%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs)
17. Katherine Lee, Orhan Firat, Ashish Agarwal, Clara Fannjiang, and David Sussillo. 2018. Hallucinations in neural machine translation. [find](https://scholar.google.com/scholar?q=Katherine+Lee%2C+Orhan+Firat%2C+Ashish+Agarwal%2C+Clara+Fannjiang%2C+and+David+Sussillo%2E+2018%2E+Hallucinations+in+neural+machine+translation%2E)
18. Eliza Mik. 2024. Caveat lector: Large language models in legal practice. Preprint, arXiv:2403.09163. [find](https://scholar.google.com/scholar?q=Eliza+Mik%2E+2024%2E+Caveat+lector%3A+Large+language+models+in+legal+practice%2E+Preprint%2C+arXiv%3A2403%2E09163%2E)
19. Ankit Pal, Logesh Kumar Umapathi, and Malaikannan Sankarasubbu. 2023. [Med-HALT: Medical domain hallucination test for large language models](https://md.research.elamur.ai/free/en/papers/pal-2023-med-halt-medical-domain-hallucination/). In Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL), pages 314–334, Singapore. Association for Computational Linguistics.
20. Yan Pan, Davide Cadamuro, and Georg Groh. 2024. Exploring hallucinations in task-oriented dialogue systems with narrow domains. In Proceedings of the 38th Pacific Asia Conference on Language, Information and Computation, pages 609–618. [find](https://scholar.google.com/scholar?q=Yan+Pan%2C+Davide+Cadamuro%2C+and+Georg+Groh%2E+2024%2E+Exploring+hallucinations+in+task%2Doriented+dialogue+systems+with+narrow+domains%2E+In+Proceedings+of+the+38th+Pacific+Asia+Conference+on+Language%2C+Informat)
21. Vipula Rawte, Amit Sheth, and Amitava Das. 2023. [A survey of hallucination in large foundation models](https://md.research.elamur.ai/free/en/papers/rawte-2023-survey-hallucination-large-foundation-models/). Preprint, arXiv:2309.05922.
22. Nils Reimers and Iryna Gurevych. 2019. [Sentence-bert: Sentence embeddings using siamese bert-networks](https://md.research.elamur.ai/free/en/papers/reimers-2019-sentence-bert-sentence-embeddings-siamese/). In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics.
23. Pritika Rohera, Chaitrali Ginimav, Gayatri Sawant, and Raviraj Joshi. 2025. Better to ask in english? evaluating factual accuracy of multilingual llms in english and low-resource languages. Preprint, arXiv:2504.20022. — [arXiv:2504.20022](https://arxiv.org/abs/2504.20022) [find](https://scholar.google.com/scholar?q=Pritika+Rohera%2C+Chaitrali+Ginimav%2C+Gayatri+Sawant%2C+and+Raviraj+Joshi%2E+2025%2E+Better+to+ask+in+english%3F+evaluating+factual+accuracy+of+multilingual+llms+in+english+and+low%2Dresource+languages%2E+Preprint%2C+)
24. Pranab Sahoo, Prabhash Meharia, Akash Ghosh, Sriparna Saha, Vinija Jain, and Aman Chadha. 2024. A comprehensive survey of hallucination in large language, image, video and audio foundation models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 11709–11724, Miami, Flo… [find](https://scholar.google.com/scholar?q=Pranab+Sahoo%2C+Prabhash+Meharia%2C+Akash+Ghosh%2C+Sriparna+Saha%2C+Vinija+Jain%2C+and+Aman+Chadha%2E+2024%2E+A+comprehensive+survey+of+hallucination+in+large+language%2C+image%2C+video+and+audio+foundation+models%2E+In+)
25. Konstantinos C Siontis, Zachi I Attia, Samuel J Asirvatham, and Paul A Friedman. 2023. Chatgpt hallucinating: can it get any more humanlike? European Heart Journal, 45(5):321–323. [find](https://scholar.google.com/scholar?q=Konstantinos+C+Siontis%2C+Zachi+I+Attia%2C+Samuel+J+Asirvatham%2C+and+Paul+A+Friedman%2E+2023%2E+Chatgpt+hallucinating%3A+can+it+get+any+more+humanlike%3F+European+Heart+Journal%2C+45%285%29%3A321%E2%80%93323%2E)
26. Shamane Siriwardhana, Rivindu Weerasekera, Elliott Wen, Tharindu Kaluarachchi, Rajib Rana, and Suranga Nanayakkara. 2023. [Improving the domain adaptation of retrieval augmented generation (rag) models for open domain question answering](https://md.research.elamur.ai/free/en/papers/siriwardhana-2023-improving-domain-adaptation-retrieval-augmented/). Transactions of the Association for Computational Linguistics,…
27. Raúl Vázquez, Timothee Mickus, Elaine Zosa, Teemu Vahtola, Jörg Tiedemann, Aman Sinha, Vincent Segonne, Fernando Sánchez-Vega, Alessandro Raganato, Jindřich Libovickỳ, and 1 others. 2025. Semeval-2025 task 3: Mu-shroom, the multilingual shared task on hallucinations and related observable overgene… [find](https://scholar.google.com/scholar?q=Ra%C3%BAl+V%C3%A1zquez%2C+Timothee+Mickus%2C+Elaine+Zosa%2C+Teemu+Vahtola%2C+J%C3%B6rg+Tiedemann%2C+Aman+Sinha%2C+Vincent+Segonne%2C+Fernando+S%C3%A1nchez%2DVega%2C+Alessandro+Raganato%2C+Jindr%CC%8Cich+Libovicky%CC%80%2C+and+1+others%2E+2025%2E+Semeval%2D20)
28. Jun Xu, Hao Zhang, Haijing Zhang, Jiawei Lu, and Gang Xiao. 2024. Chattf: A knowledge graph-enhanced intelligent qa system for mitigating factuality hallucinations in traditional folklore. IEEE Access, 12:162638–162650. [find](https://scholar.google.com/scholar?q=Jun+Xu%2C+Hao+Zhang%2C+Haijing+Zhang%2C+Jiawei+Lu%2C+and+Gang+Xiao%2E+2024%2E+Chattf%3A+A+knowledge+graph%2Denhanced+intelligent+qa+system+for+mitigating+factuality+hallucinations+in+traditional+folklore%2E+IEEE+Access)
29. Ziwei Xu, Sanjay Jain, and Mohan Kankanhalli. 2025. [Hallucination is inevitable: An innate limitation of large language models](https://md.research.elamur.ai/free/en/papers/xu-2024-hallucination-inevitable-innate-limitation-large/). Preprint, arXiv:2401.11817.
30. Muru Zhang, Ofir Press, William Merrill, Alisa Liu, and Noah A. Smith. 2023. [How language model hallucinations can snowball](https://md.research.elamur.ai/free/en/papers/zhang-2023-language-model-hallucinations-snowball/). Preprint, arXiv:2305.13534.
31. Wenxuan Zhang, Hou Pong Chan, Yiran Zhao, Mahani Aljunied, Jianyu Wang, Chaoqun Liu, Yue Deng, Zhiqiang Hu, Weiwen Xu, Yew Ken Chia, and 1 others. 2025. Seallms 3: Open foundation and chat multilingual large language models for southeast asian languages. In Proceedings of the 2025 Conference of the… [find](https://scholar.google.com/scholar?q=Wenxuan+Zhang%2C+Hou+Pong+Chan%2C+Yiran+Zhao%2C+Mahani+Aljunied%2C+Jianyu+Wang%2C+Chaoqun+Liu%2C+Yue+Deng%2C+Zhiqiang+Hu%2C+Weiwen+Xu%2C+Yew+Ken+Chia%2C+and+1+others%2E+2025%2E+Seallms+3%3A+Open+foundation+and+chat+multilingua)
32. Zhihong Zhu, Yunyan Zhang, Xianwei Zhuang, Fan Zhang, Zhongwei Wan, Yuyan Chen, Qingqing-Long QingqingLong, Yefeng Zheng, and Xian Wu. 2025. Can we trust AI doctors? a survey of medical hallucination in large language and large vision-language models. In Findings of the Association for Computational… [find](https://scholar.google.com/scholar?q=Zhihong+Zhu%2C+Yunyan+Zhang%2C+Xianwei+Zhuang%2C+Fan+Zhang%2C+Zhongwei+Wan%2C+Yuyan+Chen%2C+Qingqing%2DLong+QingqingLong%2C+Yefeng+Zheng%2C+and+Xian+Wu%2E+2025%2E+Can+we+trust+AI+doctors%3F+a+survey+of+medical+hallucination+)

*Updated 31 October 2026*