arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.17045cs.CL
收藏

大语言模型无需规划即可说服理论之心理论

Large Language Models Persuade Without Planning Theory of Mind

Stanford University(斯坦福大学);University of St. Andrews(圣安德鲁斯大学);Cornell University(康奈尔大学);University of Cambridge(剑桥大学);Stony Brook University(石溪大学)

Jared Moore, Rasmus Overmark, Ned Cooper, Beba Cibralic, Nick Haber, Cameron R. Jones

AI总结:

大语言模型通过战略性揭示信息说服目标,无需显式理论之心推理,实验显示其在说服任务中表现优于人类。

摘要:

越来越多的研究试图通过静态、非互动的问题和答案基准来评估人类和大语言模型(LLMs)的理论之心(ToM)能力。然而,该领域理论工作表明,第一人称互动是理论之心的关键部分,而此类预测、观众任务可能无法评估它。我们通过一个新颖的理论之心任务来填补这一空白,该任务要求代理通过战略性地揭示信息来说服目标选择三个政策提案之一。成功取决于说服者的敏感性,即给定目标的知识状态(目标对政策了解什么)和动机状态(目标对不同结果的价值程度)。我们变化了这些状态是否被揭示给说服者或隐藏,此时说服者必须询问或推断它们。在实验1中,参与者说服了一个只进行理性推断的机器人。LLMs在揭示条件下表现出色,但在隐藏条件下表现低于偶然,这表明在提取和使用心理状态信息方面存在困难。人类在两种条件下表现中等,表明具备参与此类规划的能力。在实验2中,其中一个人类目标角色扮演机器人,以及在实验3中,其中我们测量了人类目标的真实信念是否发生变化,LLMs在所有条件下均优于人类说服者。这些结果表明,有效的说服可以在没有显式理论之心推理(例如通过修辞策略)的情况下发生,并且LLMs在这一形式的说服中表现优异。总体而言,我们的结果警示不要将人类般的理论之心归因于LLMs,同时突显LLMs影响人们信念和行为的潜力。

英文摘要:

A growing body of work attempts to evaluate the theory of mind (ToM) abilities of humans and large language models (LLMs) using static, non-interactive question-and-answer benchmarks. However, theoretical work in the field suggests that first-personal interaction is a crucial part of ToM and that such predictive, spectatorial tasks may fail to evaluate it. We address this gap with a novel ToM task that requires an agent to persuade a target to choose one of three policy proposals by strategically revealing information. Success depends on a persuader's sensitivity to a given target's knowledge states (what the target knows about the policies) and motivational states (how much the target values different outcomes). We varied whether these states were Revealed to persuaders or Hidden, in which case persuaders had to inquire about or infer them. In Experiment 1, participants persuaded a bot programmed to make only rational inferences. LLMs excelled in the Revealed condition but performed below chance in the Hidden condition, suggesting difficulty with the multi-step planning required to elicit and use mental state information. Humans performed moderately well in both conditions, indicating an ability to engage such planning. In Experiment 2, where a human target role-played the bot, and in Experiment 3, where we measured whether human targets' real beliefs changed, LLMs outperformed human persuaders across all conditions. These results suggest that effective persuasion can occur without explicit ToM reasoning (e.g., through rhetorical strategies) and that LLMs excel at this form of persuasion. Overall, our results caution against attributing human-like ToM to LLMs while highlighting LLMs' potential to influence people's beliefs and behavior.

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。

↑