arXiv:2510.19723cs.CL2025-10被引 1

构建法律对话数据集与框架,让普通人也能轻松理解欧盟法规

From Answers to Guidance: A Proactive Dialogue System for Legal Documents

  • 用博客构建多轮对话数据集,支持主动引导式问答
  • 平均每轮对话4.3次交互,结构化回答覆盖法律要点
  • 适合法律科技、人机对话研究者参考

法律信息的可及性始终是难题,尤其对普通民众理解复杂制度文本而言。尽管欧盟开放获取立法、议会回应和监管文件,但普通用户仍难探索。本文提出EUDial,一个基于204篇由欧洲议会研究服务处公民咨询部门(AskEP)整理的博客构建的主动式多轮对话数据集,包含880个对话回合(平均每条对话4.3轮),每轮包括初始问题、结构化回答及后续追问。此外,我们提出LexGuide框架,利用分层主题组织的检索增强生成技术,实现对话流程的结构化推进,确保法律内容覆盖全面且语义连贯。实验表明,主动式、结构化导航有效缩小了法律信息可得性与公众理解之间的差距,证明EUDial与LexGuide在推动主动式法律对话系统方面具有实际应用价值。

原文摘要 · Abstract (English)

The accessibility of legal information remains a constant challenge, particularly for laypersons seeking to understand and apply complex institutional texts. While the European Union provides open access to legislation, parliamentary responses, and regulatory documents, these resources can be challenging for laypeople to explore. In this paper, we introduce EUDial, a proactive multi-turn dialogue dataset constructed from 204 blogs curated by the Citizens' Enquiries Unit (AskEP) of the European Parliamentary Research Service. EUDial contains 880 dialogue turns (averaging 4.3 turns per dialogue), where each dialogue includes initial questions, structured answers, and follow-up questions. Beyond dataset construction, we propose the LexGuide framework that leverages retrieval-augmented generation with hierarchical topic organization to structure dialogue progression, ensuring both comprehensive coverage of legal aspects and coherence across conversational turns. The results demonstrate that proactive, structured navigation closes the gap between the availability of legal information and citizen comprehension, establishing EUDial and LexGuide as practical resources for advancing proactive legal dialogue systems.

法律AI对话系统主动对话

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。