arXiv 2506.024612025-06-03cs.CL

XToM：探索大语言模型的多语言心智理论

XToM: Exploring the Multilingual Theory of Mind for Large Language Models

HKUST, Hong Kong（香港理工大学）；NVIDIA AI Technology Center (NVAITC), USA（NVIDIA AI技术中心（NVAITC））；Shanghai Jiao Tong University, China（上海交通大学）；Technische Universtität Darmstadt, Germany（德累斯顿技术大学）；LMU Munich, Germany（慕尼黑大学）；Munich Center for Machine Learning, Germany（慕尼黑机器学习中心）

Chunkit Chan, Yauwai Yim, Hongchuan Zeng, Zhiying Zou, Xinyuan Cheng, Zhifan Sun, Zheye Deng, Kawai Chung, Yuzhuo Ao, Yixiang Fan, Cheng Jiayang, Ercong Nie, Gi… 展开作者

Chunkit Chan, Yauwai Yim, Hongchuan Zeng, Zhiying Zou, Xinyuan Cheng, Zhifan Sun, Zheye Deng, Kawai Chung, Yuzhuo Ao, Yixiang Fan, Cheng Jiayang, Ercong Nie, Ginny Y. Wong, Helmut Schmid, Hinrich Schütze, Simon See, Yangqiu Song

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出多语言心智理论基准XToM，覆盖五种语言和丰富任务场景，系统评估LLM后发现其多语言理解能力强但ToM表现因语言而异，揭示了跨语言心智化能力的局限。

摘要：

心智理论（ToM）指推断他人心理状态的能力，是人类社会认知的关键。现有对大语言模型（LLM）的ToM评估大多局限于英语，忽视了塑造人类认知的语言多样性。这一局限引出一个关键问题：LLM能否展现多语言心智理论，即在不同语言语境中推理心理状态的能力？为填补这一空白，我们提出了XToM，一个经过严格验证的多语言基准，它在五种语言上评估ToM，并纳入多样且语境丰富的任务场景。利用XToM，我们系统评估了LLM（如DeepSeek R1），揭示出明显的不一致：尽管模型在多语言语言理解方面表现出色，其ToM表现却因语言而异。我们的发现暴露了LLM在跨语言语境中复现类人心智化能力方面的局限。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。