Dual Hierarchical Dialogue Policy Learning for Legal Inquisitive Conversational Agents
Quick Answer
The paper introduces Inquisitive Conversational Agents (ICAs) designed for U.S.
Quick Take
Supreme Court oral arguments, utilizing a Dual Hierarchical Reinforcement Learning framework with two cooperating agents. Evaluations demonstrate that this approach outperforms various baselines, marking a significant advancement in proactive dialogue systems for legal applications.
Key Points
- Introduces Inquisitive Conversational Agents (ICAs) for proactive information extraction.
- Utilizes a Dual Hierarchical Reinforcement Learning framework with two cooperating agents.
- Emulates judicial questioning patterns to uncover crucial legal information.
- Outperforms various baselines on a U.S. Supreme Court dataset across multiple metrics.
- Represents a significant step toward high-stakes, domain-specific conversational applications.
Paper Resources
Article Excerpt
From source RSS / original summaryarXiv:2605. 14057v1 Announce Type: new Abstract: 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 \emph{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.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →TriAgent: Divergence-Aware Committees for Cost-Efficient Financial Sentiment Analysis
TriAgent introduces a cost-efficient multi-agent system for financial sentiment analysis, combining VADER, FinBERT, and Qwen2.5. It achieves an F1 score of ~0.87 with significant savings of $9.3M/year at a 10M-user scale compared to GPT-4o-mini, while also detecting hallucinations with an AUC of 0.90.