研究人与大模型对话中双向影响，发现个性化聊天更易导致双方立场趋同。
Beyond One-Way Influence: Bidirectional Opinion Dynamics in Multi-Turn Human-LLM Interactions
- 通过三类对话实验，分析用户与大模型在多轮交流中的双向影响机制。
- 用户立场变化小，但大模型输出明显调整，尤其在个性化设置下差距缩小。
- 分享个人经历的对话最易引发双方立场改变，提示需警惕过度对齐风险。
基于大语言模型的聊天机器人日益用于观点探索。以往研究主要关注大模型如何影响用户观点，但很少深入探讨用户输入如何反向影响大模型回应，以及这种双向影响在多轮对话中的表现。本研究通过50场涉及争议话题的对话（共266名参与者）开展实验，对比三种情境：静态陈述、标准聊天机器人和个性化聊天机器人。结果表明，用户观点几乎未发生显著变化，而大模型输出则出现明显调整，缩小了人与模型立场间的差距。个性化设置进一步放大了双向影响。多轮对话分析显示，包含参与者个人故事的交流最易引发人类与模型立场的改变。研究揭示了人机交互中过度对齐的风险，强调需谨慎设计个性化聊天机器人以实现更稳健、审慎的观点对齐。
原文摘要 · Abstract (English)
Large language model (LLM)-powered chatbots are increasingly used for opinion exploration. Prior research examined how LLMs alter user views, yet little work extended beyond one-way influence to address how user input can affect LLM responses and how such bi-directional influence manifests throughout the multi-turn conversations. This study investigates this dynamic through 50 controversial-topic discussions with participants (N=266) across three conditions: static statements, standard chatbot, and personalized chatbot. Results show that human opinions barely shifted, while LLM outputs changed more substantially, narrowing the gap between human and LLM stance. Personalization amplified these shifts in both directions compared to the standard setting. Analysis of multi-turn conversations further revealed that exchanges involving participants' personal stories were most likely to trigger stance changes for both humans and LLMs. Our work highlights the risk of over-alignment in human-LLM interaction and the need for careful design of personalized chatbots to more thoughtfully and stably align with users.
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。