From Answers to Guidance: A Proactive Dialogue System for Legal Documents
Ashish Chouhan, Michael Gertz

TL;DR
This paper introduces EUDial, a dataset of legal dialogues, and LexGuide, a retrieval-augmented framework that improves proactive legal guidance through structured multi-turn conversations, aiding laypersons in understanding complex legal texts.
Contribution
The paper presents a novel dataset and a hierarchical retrieval-augmented generation framework for proactive legal dialogue systems, enhancing citizen comprehension of legal information.
Findings
EUDial dataset contains 880 dialogue turns from citizen inquiries.
LexGuide effectively structures legal dialogues with hierarchical topic organization.
Proactive dialogue system improves legal information accessibility for laypersons.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Artificial Intelligence in Law · Multi-Agent Systems and Negotiation
