大模型对话中身份会随时间漂移，越大越明显。
Examining Identity Drift in Conversations of LLM Agents
- 用多轮个人主题对话测试九个大模型的身份一致性
- 参数量越大，身份漂移越严重，最大漂移达38%
- 给定角色设定未必能稳定身份，适合长期对话系统优化
大型语言模型（LLMs）在对话中表现出色，但常出现身份漂移问题，即交互模式或风格随时间变化。本研究考察了九个LLM在身份一致性方面的表现，重点分析模型家族、参数规模及角色设定类型的影响。通过多轮个人主题对话，结合定性与定量分析，发现三个结论：（1）参数量更大的模型身份漂移更显著，最大漂移率达38%；（2）模型家族差异存在，但影响弱于参数规模；（3）提供角色设定未必能缓解身份漂移。这些发现有助于提升人工智能对话系统在长期交互中的角色稳定性。
原文摘要 · Abstract (English)
Large Language Models (LLMs) show impressive conversational abilities but sometimes show identity drift problems, where their interaction patterns or styles change over time. As the problem has not been thoroughly examined yet, this study examines identity consistency across nine LLMs. Specifically, we (1) investigate whether LLMs could maintain consistent patterns (or identity) and (2) analyze the effect of the model family, parameter sizes, and provided persona types. Our experiments involve multi-turn conversations on personal themes, analyzed in qualitative and quantitative ways. Experimental results indicate three findings. (1) Larger models experience greater identity drift. (2) Model differences exist, but their effect is not stronger than parameter sizes. (3) Assigning a persona may not help to maintain identity. We hope these three findings can help to improve persona stability in AI-driven dialogue systems, particularly in long-term conversations.
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。