LLM与人类能各自形成沟通惯例，但彼此难以对齐。
LLMs and people both learn to form conventions -- just not with each other
- 让同类型对话对（人-人、AI-AI）进行多模态对话，观察惯例形成
- 异质对（人-AI）虽消息变短，但准确率和词汇重叠仍显著更低
- 单纯模仿人类表达无法实现真正对齐，需共享意义理解偏好
人类在对话中会自发形成共享的沟通惯例以提升交流效率。我们测试大语言模型是否也能在多模态通信游戏中形成类似惯例。在同类型配对（人-人、AI-AI）中，双方均表现出惯例形成的迹象：回应准确性提高、一致性增强、消息长度缩短。然而，在异质人机配对中，这一趋势未能成立，表明双方沟通倾向存在差异。在第二项实验中，我们通过提示让模型生成看似人类的表达，尽管其消息长度接近人类配对水平，但准确率和词汇重叠仍显著低于人-人及AI-AI配对。结果表明，对话对齐不仅需要模仿行为，更依赖于对意义传达的共同解释偏差。
原文摘要 · Abstract (English)
Humans align to one another in conversation -- adopting shared conventions that ease communication. We test whether LLMs form the same kinds of conventions in a multimodal communication game. Both humans and LLMs display evidence of convention-formation (increasing the accuracy and consistency of their turns while decreasing their length) when communicating in same-type dyads (humans with humans, AI with AI). However, heterogenous human-AI pairs fail -- suggesting differences in communicative tendencies. In Experiment 2, we ask whether LLMs can be induced to behave more like human conversants, by prompting them to produce superficially humanlike behavior. While the length of their messages matches that of human pairs, accuracy and lexical overlap in human-LLM pairs continues to lag behind that of both human-human and AI-AI pairs. These results suggest that conversational alignment requires more than just the ability to mimic previous interactions, but also shared interpretative biases toward the meanings that are conveyed.
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。