XToM: Exploring the Multilingual Theory of Mind for Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918044292349952 |
|---|---|
| author | Chan, Chunkit Yim, Yauwai Zeng, Hongchuan Zou, Zhiying Cheng, Xinyuan Sun, Zhifan Deng, Zheye Chung, Kawai Ao, Yuzhuo Fan, Yixiang Jiayang, Cheng Nie, Ercong Wong, Ginny Y. Schmid, Helmut Schütze, Hinrich See, Simon Song, Yangqiu |
| author_facet | Chan, Chunkit Yim, Yauwai Zeng, Hongchuan Zou, Zhiying Cheng, Xinyuan Sun, Zhifan Deng, Zheye Chung, Kawai Ao, Yuzhuo Fan, Yixiang Jiayang, Cheng Nie, Ercong Wong, Ginny Y. Schmid, Helmut Schütze, Hinrich See, Simon Song, Yangqiu |
| contents | Theory of Mind (ToM), the ability to infer mental states in others, is pivotal for human social cognition. Existing evaluations of ToM in LLMs are largely limited to English, neglecting the linguistic diversity that shapes human cognition. This limitation raises a critical question: can LLMs exhibit Multilingual Theory of Mind, which is the capacity to reason about mental states across diverse linguistic contexts? To address this gap, we present XToM, a rigorously validated multilingual benchmark that evaluates ToM across five languages and incorporates diverse, contextually rich task scenarios. Using XToM, we systematically evaluate LLMs (e.g., DeepSeek R1), revealing a pronounced dissonance: while models excel in multilingual language understanding, their ToM performance varies across languages. Our findings expose limitations in LLMs' ability to replicate human-like mentalizing across linguistic contexts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_02461 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | XToM: Exploring the Multilingual Theory of Mind for Large Language Models Chan, Chunkit Yim, Yauwai Zeng, Hongchuan Zou, Zhiying Cheng, Xinyuan Sun, Zhifan Deng, Zheye Chung, Kawai Ao, Yuzhuo Fan, Yixiang Jiayang, Cheng Nie, Ercong Wong, Ginny Y. Schmid, Helmut Schütze, Hinrich See, Simon Song, Yangqiu Computation and Language Theory of Mind (ToM), the ability to infer mental states in others, is pivotal for human social cognition. Existing evaluations of ToM in LLMs are largely limited to English, neglecting the linguistic diversity that shapes human cognition. This limitation raises a critical question: can LLMs exhibit Multilingual Theory of Mind, which is the capacity to reason about mental states across diverse linguistic contexts? To address this gap, we present XToM, a rigorously validated multilingual benchmark that evaluates ToM across five languages and incorporates diverse, contextually rich task scenarios. Using XToM, we systematically evaluate LLMs (e.g., DeepSeek R1), revealing a pronounced dissonance: while models excel in multilingual language understanding, their ToM performance varies across languages. Our findings expose limitations in LLMs' ability to replicate human-like mentalizing across linguistic contexts. |
| title | XToM: Exploring the Multilingual Theory of Mind for Large Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2506.02461 |