---
title: "Can Small LLMs Learn a Robust Theory of Mind via RLVR?"
description: "The authors use the false-belief task as a test case. 30 references. Among them: 0."
authors: ["Sneheel Sarangi", "Hanan Salam"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.2061/"
doi: "10.18653/v1/2026.findings-acl.2061"
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/sarangi-2026-can-small-llms-learn-robust/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/sarangi-2026-can-small-llms-learn-robust/)

[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/24/) / Can Small LLMs Learn a Robust Theory of Mind via RLVR? Investigating Generalization through the False-Belief Task

# Can Small LLMs Learn a Robust Theory of Mind via RLVR? Investigating Generalization through the False-Belief Task

**Authors:** [Sneheel Sarangi](https://md.research.elamur.ai/free/en/authors/sneheel-sarangi/) and [Hanan Salam](https://md.research.elamur.ai/free/en/authors/hanan-salam/) · **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.2061/) · [PDF](https://aclanthology.org/2026.findings-acl.2061.pdf) · [DOI 10.18653/v1/2026.findings-acl.2061](https://doi.org/10.18653/v1/2026.findings-acl.2061) · [OpenAlex](https://openalex.org/W7166840339)

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

## Summary
The paper asks whether reinforcement learning with verifiable rewards (RLVR), which has improved mathematical and logical reasoning, can give small LLMs a general Theory of Mind (ToM) rather than benchmark-specific skill. The authors use the false-belief task as a test case. They fine-tune Qwen2.5-7B-Instruct with GRPO, using a rule-based reward that checks output format and then answer correctness. Training uses every combination of three ToM datasets: HiToM, ExploreToM and FANToM. They then measure zero-shot transfer to held-out benchmarks and tasks.

RLVR raises in-distribution accuracy sharply, and training on all three datasets together gives the best in-distribution results. Gains on unseen benchmarks, however, are small or absent. Out-of-distribution accuracy also swings widely between checkpoints of the same run, and an improvement on one held-out benchmark does not carry over to others.

The authors conclude that the models learn dataset-specific pattern matching, not an abstract model of mental states. This suggests that RLVR's success in formal domains does not automatically extend to social cognition.

## Key points
- The evaluation suite covers 5 ToM benchmarks with 13 tasks. Held out for testing are:
  - all of OpenToM;
  - ToMBench (false-belief portion only);
  - the FANToM list-response tasks;
  - fourth-order HiToM questions.
- Seven models were trained, one per dataset combination. A training unit is 900 samples per dataset, and some runs scale HiToM and ExploreToM data up to 5x.
- Out-of-distribution scores are unstable. In the Hi-Exp run, FANToM accuracy went from 28% to 46% at step 4000 and then fell to 14% at the next checkpoint, while in-distribution accuracy stayed flat.
- A HiToM ablation points to "statistical hacking": models trained on lower-order tasks can score better on harder higher-order ones.
- The appendices report the same trends with other model sizes, an SFT baseline and REINFORCE++. Stated limitations are the absence of larger models and the simple correctness-only reward.

*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

- [New York University](https://md.research.elamur.ai/free/en/universities/new-york-university/) — University, New York, United States · 201 works · 100,180 citations
- [New York University Abu Dhabi](https://md.research.elamur.ai/free/en/universities/new-york-university-abu-dhabi/) — University, Abu Dhabi, United Arab Emirates · 122 works · 4,602 citations
- [McGill University](https://md.research.elamur.ai/free/en/universities/mcgill-university/) — University, Montreal, Canada · 87 works · 11,027 citations

📚 Shelves (7): [🖥️ 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 · [💭 Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/) · 1,552 works · [💭 Developmental and Educational Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/developmental-and-educational-psychology/) · 499 works

🧭 Topics (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works

## Cite

Cite as: Sneheel Sarangi and Hanan Salam. 2026. Can Small LLMs Learn a Robust Theory of Mind via RLVR? Investigating Generalization through the False-Belief Task. 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{sarangi2026can,
  title = {{Can Small LLMs Learn a Robust Theory of Mind via RLVR? Investigating Generalization through the False-Belief Task}},
  author = {Sneheel Sarangi and Hanan Salam},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.2061},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.2061}
}
```

- [← previous Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment](https://md.research.elamur.ai/free/en/papers/tan-2026-can-persona-prompted-llms-emulate/)
- [next → Can Spectral-Clipping Enable Better Learning While Forgetting Less for Low-Rank Adaptation?](https://md.research.elamur.ai/free/en/papers/wi-2026-can-spectral-clipping-enable-better/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/24/)

## References

30 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Md Tanvirul Alam and Nidhi Rastogi. 2025. Limits of generalization in rlvr: Two case studies in mathematical reasoning. Preprint, arXiv:2510.27044. [find](https://scholar.google.com/scholar?q=Md+Tanvirul+Alam+and+Nidhi+Rastogi%2E+2025%2E+Limits+of+generalization+in+rlvr%3A+Two+case+studies+in+mathematical+reasoning%2E+Preprint%2C+arXiv%3A2510%2E27044%2E)
2. Simon Baron-Cohen. 1995. Mindblindness: An Essay on Autism and Theory of Mind. The MIT Press. [find](https://scholar.google.com/scholar?q=Simon+Baron%2DCohen%2E+1995%2E+Mindblindness%3A+An+Essay+on+Autism+and+Theory+of+Mind%2E+The+MIT+Press%2E)
3. Zhuang Chen, Jincenzi Wu, Jinfeng Zhou, Bosi Wen, Guanqun Bi, Gongyao Jiang, Yaru Cao, Mengting Hu, Yunghwei Lai, Zexuan Xiong, and Minlie Huang. 2024. [ToMBench: Benchmarking theory of mind in large language models](https://md.research.elamur.ai/free/en/papers/chen-2024-tombench-benchmarking-theory-mind-large/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Lingu…
4. DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, Aixin Liu, Bing Xue, Bingxuan Wang, Bochao Wu, Bei Feng, Chengda Lu, Chengg… [find](https://scholar.google.com/scholar?q=DeepSeek%2DAI%2C+Daya+Guo%2C+Dejian+Yang%2C+Haowei+Zhang%2C+Junxiao+Song%2C+Ruoyu+Zhang%2C+Runxin+Xu%2C+Qihao+Zhu%2C+Shirong+Ma%2C+Peiyi+Wang%2C+Xiao+Bi%2C+Xiaokang+Zhang%2C+Xingkai+Yu%2C+Yu+Wu%2C+Z%2E+F%2E+Wu%2C+Zhibin+Gou%2C+Zhihong+Sha)
5. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, Arun Rao,… — [The Llama 3 Herd of Models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/)
6. Jian Hu, Jason Klein Liu, and Wei Shen. 2025. Reinforce++: An efficient rlhf algorithm with robustness to both prompt and reward models. Preprint, arXiv:2501.03262. [find](https://scholar.google.com/scholar?q=Jian+Hu%2C+Jason+Klein+Liu%2C+and+Wei+Shen%2E+2025%2E+Reinforce%2B%2B%3A+An+efficient+rlhf+algorithm+with+robustness+to+both+prompt+and+reward+models%2E+Preprint%2C+arXiv%3A2501%2E03262%2E)
7. Hyunwoo Kim, Melanie Sclar, Xuhui Zhou, Ronan Bras, Gunhee Kim, Yejin Choi, and Maarten Sap. 2023. FANToM: A benchmark for stress-testing machine theory of mind in interactions. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 14397–14413, Singapore. A… [find](https://scholar.google.com/scholar?q=Hyunwoo+Kim%2C+Melanie+Sclar%2C+Xuhui+Zhou%2C+Ronan+Bras%2C+Gunhee+Kim%2C+Yejin+Choi%2C+and+Maarten+Sap%2E+2023%2E+FANToM%3A+A+benchmark+for+stress%2Dtesting+machine+theory+of+mind+in+interactions%2E+In+Proceedings+of+the+)
8. Michal Kosinski. 2023. [Theory of mind may have spontaneously emerged in large language models](https://md.research.elamur.ai/free/en/papers/kosinski-2023-evaluating-large-language-models-theory/). Preprint, arXiv:2302.02083.
9. Nathan Lambert, Jacob Morrison, Valentina Pyatkin, Shengyi Huang, Hamish Ivison, Faeze Brahman, Lester James V. Miranda, Alisa Liu, Nouha Dziri, Shane Lyu, Yuling Gu, Saumya Malik, Victoria Graf, Jena D. Hwang, Jiangjiang Yang, Ronan Le Bras, Oyvind Tafjord, Chris Wilhelm, Luca Soldaini, Noah A. Smi… — [Tulu 3: Pushing Frontiers in Open Language Model Post-Training](https://md.research.elamur.ai/free/en/papers/lambert-2024-tulu-3-pushing-frontiers-open/)
10. Matthew Le, Y-Lan Boureau, and Maximilian Nickel. 2019. Revisiting the evaluation of theory of mind through question answering. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-I… [find](https://scholar.google.com/scholar?q=Matthew+Le%2C+Y%2DLan+Boureau%2C+and+Maximilian+Nickel%2E+2019%2E+Revisiting+the+evaluation+of+theory+of+mind+through+question+answering%2E+In+Proceedings+of+the+2019+Conference+on+Empirical+Methods+in+Natural+La)
11. Yi-Long Lu, Chunhui Zhang, Jiajun Song, Lifeng Fan, and Wei Wang. 2025. Do theory of mind benchmarks need explicit human-like reasoning in language models? Preprint, arXiv:2504.01698. — [arXiv:2504.01698](https://arxiv.org/abs/2504.01698) [find](https://scholar.google.com/scholar?q=Yi%2DLong+Lu%2C+Chunhui+Zhang%2C+Jiajun+Song%2C+Lifeng+Fan%2C+and+Wei+Wang%2E+2025%2E+Do+theory+of+mind+benchmarks+need+explicit+human%2Dlike+reasoning+in+language+models%3F+Preprint%2C+arXiv%3A2504%2E01698%2E+%E2%80%94+%5BarXiv%3A2504%2E01)
12. Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul Christiano, Jan Leike, and Ryan Lowe. 2022. [Train…](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/)
13. David Premack and Guy Woodruff. 1978. Does the chimpanzee have a theory of mind? Behavioral and Brain Sciences, 1(4):515–526. [find](https://scholar.google.com/scholar?q=David+Premack+and+Guy+Woodruff%2E+1978%2E+Does+the+chimpanzee+have+a+theory+of+mind%3F+Behavioral+and+Brain+Sciences%2C+1%284%29%3A515%E2%80%93526%2E)
14. Qwen, :, An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, Junyang Lin, Kai Dang, Keming Lu, Keqin Bao, Kexin Yang, Le Yu, Mei Li, Mingfeng… [find](https://scholar.google.com/scholar?q=Qwen%2C+%3A%2C+An+Yang%2C+Baosong+Yang%2C+Beichen+Zhang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chengyuan+Li%2C+Dayiheng+Liu%2C+Fei+Huang%2C+Haoran+Wei%2C+Huan+Lin%2C+Jian+Yang%2C+Jianhong+Tu%2C+Jianwei+Zhang%2C+Jianxin+Yang%2C+Jiaxi+)
15. Neil Rabinowitz, Frank Perbet, Francis Song, Chiyuan Zhang, S. M. Ali Eslami, and Matthew Botvinick. 2018. Machine theory of mind. In Proceedings of the 35th International Conference on Machine Learning, volume 80 of Proceedings of Machine Learning Research, pages 4218–4227. PMLR. [find](https://scholar.google.com/scholar?q=Neil+Rabinowitz%2C+Frank+Perbet%2C+Francis+Song%2C+Chiyuan+Zhang%2C+S%2E+M%2E+Ali+Eslami%2C+and+Matthew+Botvinick%2E+2018%2E+Machine+theory+of+mind%2E+In+Proceedings+of+the+35th+International+Conference+on+Machine+Learni)
16. Sneheel Sarangi, Maha Elgarf, and Hanan Salam. 2025a. [Decompose-ToM: Enhancing theory of mind reasoning in large language models through simulation and task decomposition](https://md.research.elamur.ai/free/en/papers/sarangi-2025-decompose-tom-enhancing-theory-mind/). In Proceedings of the 31st International Conference on Computational Linguistics, pages 10228–10241, Abu Dhabi, UAE. Association…
17. Sneheel Sarangi, Chetan Talele, and Hanan Salam. 2025b. Agentic-ToM: Cognition-inspired agentic processing for enhancing theory of mind reasoning. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 25645–25661, Suzhou, China. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Sneheel+Sarangi%2C+Chetan+Talele%2C+and+Hanan+Salam%2E+2025b%2E+Agentic%2DToM%3A+Cognition%2Dinspired+agentic+processing+for+enhancing+theory+of+mind+reasoning%2E+In+Findings+of+the+Association+for+Computational+Ling)
18. Melanie Sclar, Sachin Kumar, Peter West, Alane Suhr, Yejin Choi, and Yulia Tsvetkov. 2023. [Minding language models’ (lack of) theory of mind: A plug-and-play multi-character belief tracker](https://md.research.elamur.ai/free/en/papers/sclar-2023-minding-language-models-lack-theory/). In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Pap…
19. Melanie Sclar, Jane Yu, Maryam Fazel-Zarandi, Yulia Tsvetkov, Yonatan Bisk, Yejin Choi, and Asli Celikyilmaz. 2024. Explore theory of mind: Program-guided adversarial data generation for theory of mind reasoning. Preprint, arXiv:2412.12175. — [arXiv:2412.12175](https://arxiv.org/abs/2412.12175) [find](https://scholar.google.com/scholar?q=Melanie+Sclar%2C+Jane+Yu%2C+Maryam+Fazel%2DZarandi%2C+Yulia+Tsvetkov%2C+Yonatan+Bisk%2C+Yejin+Choi%2C+and+Asli+Celikyilmaz%2E+2024%2E+Explore+theory+of+mind%3A+Program%2Dguided+adversarial+data+generation+for+theory+of+min)
20. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, Y. K. Li, Y. Wu, and Daya Guo. 2024. [Deepseekmath: Pushing the limits of mathematical reasoning in open language models](https://md.research.elamur.ai/free/en/papers/shao-2024-deepseekmath-pushing-limits-mathematical-reasoning/). Preprint, arXiv:2402.03300.
21. Natalie Shapira, Mosh Levy, Seyed Hossein Alavi, Xuhui Zhou, Yejin Choi, Yoav Goldberg, Maarten Sap, and Vered Shwartz. 2023. Clever hans or neural theory of mind? stress testing social reasoning in large language models. Preprint, arXiv:2305.14763. [find](https://scholar.google.com/scholar?q=Natalie+Shapira%2C+Mosh+Levy%2C+Seyed+Hossein+Alavi%2C+Xuhui+Zhou%2C+Yejin+Choi%2C+Yoav+Goldberg%2C+Maarten+Sap%2C+and+Vered+Shwartz%2E+2023%2E+Clever+hans+or+neural+theory+of+mind%3F+stress+testing+social+reasoning+in+l)
22. Chandler Smith, Marwa Abdulhai, Manfred Diaz, Marko Tesic, Rakshit S. Trivedi, Alexander Sasha Vezhnevets, Lewis Hammond, Jesse Clifton, Minsuk Chang, Edgar A. Duéñez-Guzmán, John P. Agapiou, Jayd Matyas, Danny Karmon, Akash Kundu, Aliaksei Korshuk, Ananya Ananya, Ar-rasy Rahman, Avinaash Anand Kula… — [arXiv:2512.03318](https://arxiv.org/abs/2512.03318) [find](https://scholar.google.com/scholar?q=Chandler+Smith%2C+Marwa+Abdulhai%2C+Manfred+Diaz%2C+Marko+Tesic%2C+Rakshit+S%2E+Trivedi%2C+Alexander+Sasha+Vezhnevets%2C+Lewis+Hammond%2C+Jesse+Clifton%2C+Minsuk+Chang%2C+Edgar+A%2E+Du%C3%A9%C3%B1ez%2DGuzm%C3%A1n%2C+John+P%2E+Agapiou%2C+Jayd+Mat)
23. Bangkok, Thailand. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Bangkok%2C+Thailand%2E+Association+for+Computational+Linguistics%2E)
24. Yufan Wu, Yinghui He, Yilin Jia, Rada Mihalcea, Yulong Chen, and Naihao Deng. 2023. Hi-ToM: A benchmark for evaluating higher-order theory of mind reasoning in large language models. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 10691–10706, Singapore. Association f… [find](https://scholar.google.com/scholar?q=Yufan+Wu%2C+Yinghui+He%2C+Yilin+Jia%2C+Rada+Mihalcea%2C+Yulong+Chen%2C+and+Naihao+Deng%2E+2023%2E+Hi%2DToM%3A+A+benchmark+for+evaluating+higher%2Dorder+theory+of+mind+reasoning+in+large+language+models%2E+In+Findings+of+th)
25. Tian Xie, Zitian Gao, Qingnan Ren, Haoming Luo, Yuqian Hong, Bryan Dai, Joey Zhou, Kai Qiu, Zhirong Wu, and Chong Luo. 2025. [Logic-rl: Unleashing llm reasoning with rule-based reinforcement learning](https://md.research.elamur.ai/free/en/papers/xie-2025-logic-rl-unleashing-llm/). Preprint, arXiv:2502.14768.
26. Hainiu Xu, Runcong Zhao, Lixing Zhu, Jinhua Du, and Yulan He. 2024. OpenToM: A comprehensive benchmark for evaluating theory-of-mind reasoning capabilities of large language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pa… [find](https://scholar.google.com/scholar?q=Hainiu+Xu%2C+Runcong+Zhao%2C+Lixing+Zhu%2C+Jinhua+Du%2C+and+Yulan+He%2E+2024%2E+OpenToM%3A+A+comprehensive+benchmark+for+evaluating+theory%2Dof%2Dmind+reasoning+capabilities+of+large+language+models%2E+In+Proceedings+of+)
27. Yang Yue, Zhiqi Chen, Rui Lu, Andrew Zhao, Zhaokai Wang, Yang Yue, Shiji Song, and Gao Huang. 2025. [Does reinforcement learning really incentivize reasoning capacity in llms beyond the base model?](https://md.research.elamur.ai/free/en/papers/yue-2025-reinforcement-learning-really-incentivize-reasoning/) Preprint, arXiv:2504.13837.
28. Maximilian Puelma Touzel, Sneheel Sarangi, Austin Welch, Gayatri Krishnakumar, Dan Zhao, Zachary Yang, Hao Yu, Ethan Kosak-Hine, Tom Gibbs, Andreea Musulan, Camille Thibault, Busra Tugce Gurbuz, Reihaneh Rabbany, Jean-François Godbout, and Kellin Pelrine. 2024. A simulation system towards solving so… — [arXiv:2410.13915](https://arxiv.org/abs/2410.13915) [find](https://scholar.google.com/scholar?q=Maximilian+Puelma+Touzel%2C+Sneheel+Sarangi%2C+Austin+Welch%2C+Gayatri+Krishnakumar%2C+Dan+Zhao%2C+Zachary+Yang%2C+Hao+Yu%2C+Ethan+Kosak%2DHine%2C+Tom+Gibbs%2C+Andreea+Musulan%2C+Camille+Thibault%2C+Busra+Tugce+Gurbuz%2C+Reiha)
29. Tomer Ullman. 2023. Large language models fail on trivial alterations to theory-of-mind tasks. Preprint, arXiv:2302.08399. [find](https://scholar.google.com/scholar?q=Tomer+Ullman%2E+2023%2E+Large+language+models+fail+on+trivial+alterations+to+theory%2Dof%2Dmind+tasks%2E+Preprint%2C+arXiv%3A2302%2E08399%2E)
30. Alex Wilf, Sihyun Lee, Paul Pu Liang, and Louis-Philippe Morency. 2024. [Think twice: Perspective-taking improves large language models’ theory-of-mind capabilities](https://md.research.elamur.ai/free/en/papers/wilf-2024-think-twice-perspective-taking-improves/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8292–8308, Th…

*Updated 1 November 2026*