让对话模型学会协作推理，更懂对方的隐含意图。
Collaborative Rational Speech Act: Pragmatic Reasoning for Multi-Turn Dialog
- 基于信息论扩展理性言语行为框架，建模双方私有信息下的多轮对话
- 在参照游戏和医疗问诊中表现优于基线，对话更一致可解释
- 适合需要深度协作与社会感知的对话系统研发
随着AI系统承担协作角色，它们不仅需生成流畅语言，还需推理共享目标与信念。理性言语行为（RSA）框架为语用推理提供了严谨方法，但现有扩展难以适应多轮协作场景。本文提出协作式理性言语行为（CRSA），一种基于信息论（IT）的RSA扩展，通过优化速率-失真理论中的增益函数来建模多轮对话。该增益函数是原始RSA中最大化增益的延伸，考虑了对话双方均拥有私有信息且话语依赖对话历史的情况。我们在参照游戏和基于模板的医疗问诊对话任务上验证了CRSA的有效性。实验结果表明，相比现有基线，CRSA能产生更一致、可解释且更具协作性的行为，为构建更语用化和社会感知的语言代理铺平道路。
原文摘要 · Abstract (English)
As AI systems take on collaborative roles, they must reason about shared goals and beliefs-not just generate fluent language. The Rational Speech Act (RSA) framework offers a principled approach to pragmatic reasoning, but existing extensions face challenges in scaling to multi-turn, collaborative scenarios. In this paper, we introduce Collaborative Rational Speech Act (CRSA), an information-theoretic (IT) extension of RSA that models multi-turn dialog by optimizing a gain function adapted from rate-distortion theory. This gain is an extension of the gain model that is maximized in the original RSA model but takes into account the scenario in which both agents in a conversation have private information and produce utterances conditioned on the dialog. We demonstrate the effectiveness of CRSA on referential games and template-based doctor-patient dialogs in the medical domain. Empirical results show that CRSA yields more consistent, interpretable, and collaborative behavior than existing baselines-paving the way for more pragmatic and socially aware language agents.
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。