CA-BED：对话感知的贝叶斯实验设计
CA-BED: Conversation-Aware Bayesian Experimental Design
AI总结：
提出对话感知的贝叶斯实验设计（CA-BED），一种推理时概率对话规划框架，通过结合贝叶斯实验设计与LLM似然估计，在多个对话轮次中优化问题选择，在结构化实体推断基准上平均成功率提升21.8%，仅增加1.8轮对话。
摘要：
大型语言模型（LLM）在静态推理任务中表现出色，但在需要通过提问主动获取信息的交互场景中，其性能往往会下降。一个关键挑战在于选择能够减少不确定性同时纳入可能模糊或仅部分信息性的回应的问题。为了解决这个问题，我们提出了对话感知的贝叶斯实验设计（CA-BED），一种推理时概率对话规划框架，它将贝叶斯实验设计与基于LLM的似然估计相结合，以在多个对话轮次中优化问题选择。CA-BED维护关于假设的信念分布，预测可能的答案，并通过模拟对话树传播期望信息增益。在两个结构化实体推断基准上，CA-BED相比直接提示实现了平均21.8%的成功率提升，相对于其他信息寻求方法也有相当的增益。与直接提示相比，它仅平均增加了1.8个对话轮次就实现了这些增益。
英文摘要：
Large Language Models (LLMs) excel at static reasoning tasks, yet their performance often degrades in interactive scenarios where information must be actively acquired through questioning. A key challenge lies in selecting questions that reduce uncertainty while incorporating responses that may be ambiguous or only partially informative. To address this, we propose Conversation-Aware Bayesian Experimental Design (CA-BED), an inference-time probabilistic dialog planning framework that integrates Bayesian Experimental Design with LLM-based likelihood estimation to optimize question selection over multiple conversational turns. CA-BED maintains a belief distribution over hypotheses, anticipates possible answers, and propagates expected information gain through a simulated conversation tree. Across two structured entity-deduction benchmarks, CA-BED yields an average 21.8% improvement in success rates over direct prompting, with comparable gains relative to alternative information-seeking methods. It achieves these gains with an average increase of only 1.8 conversational turns compared to direct prompting.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
