mlsanityData to 14 Oct 2026

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

arXiv 2510.19723 ↗First posted 22 Oct 2025cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 21 of its 38 references that are in the map. First posted on arXiv 22 Oct 2025.

Builds on

21 of 38 references.

References · 21

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  3. 2017Billion-scale similarity search with GPUscited by 2,497
  4. 2022BERTopic: Neural topic modeling with a class-based TF-IDF procedurecited by 801
  5. 2023LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Modelscited by 336
  6. 2021CUAD: An Expert-Annotated NLP Dataset for Legal Contract Reviewcited by 236
  7. 2018Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Informationcited by 115
  8. 2022Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Datasetcited by 113
  9. 2019Question Answering for Privacy Policies: Combining Computational and Legal Perspectivescited by 67
  10. 2024Natural Language Processing for the Legal Domain: A Survey of Tasks, Datasets, Models, and Challengescited by 42
  11. 2022EUR-Lex-Sum: A Multi- and Cross-lingual Dataset for Long-form Summarization in the Legal Domaincited by 40
  12. 2024Docling Technical Reportcited by 34
9 more
  1. 2023A Survey on Asking Clarification Questions Datasets in Conversational Systemscited by 28
  2. 2024Leveraging Large Language Models for Learning Complex Legal Concepts through Storytellingcited by 23
  3. 2024A Survey of Conversational Searchcited by 22
  4. 2025LexRAG: Benchmarking Retrieval-Augmented Generation in Multi-Turn Legal Consultation Conversationcited by 19
  5. 2023From Text to Structure: Using Large Language Models to Support the Development of Legal Expert Systemscited by 17
  6. 2023FOLLOWUPQG: Towards Information-Seeking Follow-up Question Generationcited by 12
  7. 2025Follow-up Question Generation For Enhanced Patient-Provider Conversationscited by 10
  8. 2024LexDrafter: Terminology Drafting for Legislative Documents using Retrieval Augmented Generationcited by 6
  9. 2024Answer Retrieval in Legal Community Question Answeringcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

Similar, not cited

Close in wording, no citation either way

  1. 2025The 3rd Place Solution of CCIR CUP 2025: A Framework for Retrieval-Augmented Generation in Multi-Turn Legal Conversation
  2. 2026LawCompass: Navigating from Legal QA to Multi-Agent Deep Research with Grounded Evidence
  3. 2024Unlocking Legal Knowledge with Multi-Layered Embedding-Based Retrieval
  4. 2026Fine-grained Claim-level RAG Benchmark for Law
  5. 2023Interpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Models
  6. 2026Decompose-and-Refine: Structured Legal Question Answering with Parametric Retrieval
  7. 2024Experimenting with Legal AI Solutions: The Case of Question-Answering for Access to Justice
  8. 2024GRAF: Graph Retrieval Augmented by Facts for Romanian Legal Multi-Choice Question Answering