心理理论与亲社会信念对最后通牒博弈中大型语言模型的人类对齐行为的影响
Effects of Theory of Mind and Prosocial Beliefs on Steering Human-Aligned Behaviors of LLMs in Ultimatum Games
AI总结：
本研究以最后通牒博弈为任务，赋予LLM不同亲社会信念与推理方法，开展2700次模拟，发现ToM推理可增强LLM行为对齐度等，且不同游戏角色适配不同ToM顺序，Llama 3.3 70B的推理与行动信念最一致。
摘要：
大型语言模型（LLMs）已展现出模拟人类行为及执行心理理论（ToM）推理的潜力，这对复杂社会交互至关重要。本研究以最后通牒博弈为参照任务，探究ToM推理在使智能体行为与人类规范对齐方面的作用。我们为LLM智能体赋予不同的亲社会信念（贪婪型、公平型、无私型）及不同层级的推理方法（思维链推理、ToM推理），在包括o3-mini、DeepSeek-R1 Distilled Qwen 32B等推理模型在内的多种LLM上，检验其决策过程与结果。我们开展了2700次模拟，结果显示ToM推理可增强行为与人类的对齐度、决策一致性及谈判结果。与先前研究结果一致，推理型LLM的能力不及经ToM增强的LLM，且不同游戏角色受益于不同的ToM顺序。公平型提议者与接受提议的回应者与其战略推理最为一致，而所有智能体在拒绝提议时均与人类信念高度一致，仅当提议公平时除外。人类验证进一步显示，Llama 3.3 70B产生的推理与其行动及信念最为一致。本研究的发现深化了对ToM在人机交互及合作决策中作用的理解，实验所用代码可在该https链接获取。
英文摘要：
Large Language Models (LLMs) have shown potential in simulating human behaviors and performing theory-of-mind (ToM) reasoning, crucial for complex social interactions. We investigate ToM reasoning's role in aligning agentic behaviors with human norms in negotiation tasks, using the ultimatum game as our referenced task. We initialized LLM agents with different prosocial beliefs (Greedy, Fair, Selfless) and reasoning methods (chain of thought and ToM reasoning of varying levels), examining their decision-making process and outcome across multiple LLMs, including reasoning models like o3-mini and DeepSeek-R1 Distilled Qwen 32B. We perform 2,700 simulations to show that ToM reasoning enhances behavioral alignment with human, decision-making consistency, and negotiation outcomes. Consistent with prior findings, reasoning LLMs exhibit limited capability compared to ToM-enhanced LLMs, with different game roles benefiting from different ToM orders. Fair proposers and responders accepting offers were the most consistent with their strategic reasonings, whereas all agents showed strong consistencies with human beliefs when rejecting offers, except when the offer was fair. Human verification further revealed that Llama 3.3 70B produces reasoning most consistent with its actions and beliefs. Our findings advance understanding of ToM's role in human-AI interaction and cooperative decision-making. The code used for our experiments can be found at https://github.com/Stealth-py/UltimatumToM.
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。
