研究大模型在权力不对称对话中是否表现出人类类似的社会认知行为。
Do LLM Agents Mirror Socio-Cognitive Effects in Power-Asymmetric Conversations?
- 给大模型分配高低权力角色，模拟多轮对话
- 发现模型呈现语言协调、代词使用等权力效应
- 揭示其可能引发安全风险或有益互动的潜力
权力差异通过已知的社会认知效应影响人类沟通，包括语言协调、代词使用、权威偏见和有害顺从。本文研究当大型语言模型（LLMs）被赋予高或低地位角色时，是否会表现出类似行为。通过来自不同职业的角色设定，模拟多轮权力不对称对话（如校长-教师、法官-律师），并测量（i）语言协调性、（ii）代词使用、（iii）说服成功率、（iv）对不当请求的顺从程度。结果表明，LLMs 在不同程度上表现出关键的社会认知权力效应，虽存在细微差异与可变性，但其模拟交互与理想及非理想行为均有关联。
原文摘要 · Abstract (English)
Power differences shape human communication through well documented socio cognitive effects, including language coordination, pronoun usage, authority bias, and harmful compliance. We examine whether large language models (LLMs) exhibit similar behaviors when assigned high or low status personas. Using personas from diverse professions, we simulate multi turn, power asymmetric dialogues (e.g., principal teacher, justice lawyer) and measure (i) language coordination, (ii) pronoun usage, (iii) persuasion success, and (iv) compliance with unsafe requests. Our results show that LLMs show key socio-cognitive effects of power, albeit with nuances and variability, linking simulated interactions to both desirable and unsafe behaviors.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。