arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.14057cs.CL

双层级对话策略学习用于法律探究型对话代理

Dual Hierarchical Dialogue Policy Learning for Legal Inquisitive Conversational Agents

Georgetown University(乔治城大学);Singapore Management University(新加坡国立管理学院)

Xubo Lin, Zezhi Deng, Shihao Wang, Grace Hui Yang, Yang Deng

AI总结:

本文提出双层级强化学习框架,用于法律场景中主动提取信息的对话代理,通过协调策略管理和细粒度生成,提升法律目标达成能力。

摘要:

大多数现有对话系统是用户驱动的,主要设计用于满足用户请求。然而,在许多关键现实场景中,对话代理必须主动提取信息以实现自身目标,而非仅仅响应。为此,我们引入了探究型对话代理(ICAs),并开发了一个专门针对美国最高法院口头辩论的ICA。我们提出了一种双层级强化学习框架,包含两个协作的强化学习代理,每个都有自己的策略,以协调战略对话管理和细粒度话语生成。通过学习何时以及如何提问,代理模拟了司法提问模式,并系统地揭示关键信息以实现其法律目标。在一项美国最高法院数据集上的评估表明,我们的方法在多个指标上优于各种基线。这代表了向更广泛高风险、领域特定应用迈出的重要一步。

英文摘要:

Most existing dialogue systems are user-driven, primarily designed to fulfill user requests. However, in many critical real-world scenarios, a conversational agent must proactively extract information to achieve its own objectives rather than merely respond. To address this gap, we introduce Inquisitive Conversational Agents (ICAs) and develop an ICA specifically tailored to U.S. Supreme Court oral arguments. We propose a Dual Hierarchical Reinforcement Learning framework featuring two cooperating RL agents, each with its own policy, to coordinate strategic dialogue management and fine-grained utterance generation. By learning when and how to ask probing questions, the agent emulates judicial questioning patterns and systematically uncovers crucial information to fulfill its legal objectives. Evaluations on a U.S. Supreme Court dataset show that our method outperforms various baselines across multiple metrics. It represents an important first step toward broader high-stakes, domain-specific applications.

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。

↑