Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

LexGenie: Automated Generation of Structured Reports for European Court of Human Rights Case Law

T. Y. S. S Santosh, Mahmoud Aly, Oana Ichim, Matthias Grabmair

TL;DR

LexGenie introduces an automated LLM-based pipeline to generate structured, multi-case reports from European Court of Human Rights case law by topic. It combines keyphrase-based paragraph indexing, MMR-driven retrieval, BERTopic-HDBSCAN clustering, and iterative content generation to produce coherent outlines and subsections with citations from HUDOC. Expert and automated evaluations indicate strong structure and content quality, while ablations underscore the importance of keyphrase indexing, retrieval diversity, and reorganization for coherence. The work demonstrates scalable cross-case legal analysis and points to future extensions to additional jurisdictions and enhanced cross-sectional linking.

Abstract

Analyzing large volumes of case law to uncover evolving legal principles, across multiple cases, on a given topic is a demanding task for legal professionals. Structured topical reports provide an effective solution by summarizing key issues, principles, and judgments, enabling comprehensive legal analysis on a particular topic. While prior works have advanced query-based individual case summarization, none have extended to automatically generating multi-case structured reports. To address this, we introduce LexGenie, an automated LLM-based pipeline designed to create structured reports using the entire body of case law on user-specified topics within the European Court of Human Rights jurisdiction. LexGenie retrieves, clusters, and organizes relevant passages by topic to generate a structured outline and cohesive content for each section. Expert evaluation confirms LexGenie's utility in producing structured reports that enhance efficient, scalable legal analysis.

LexGenie: Automated Generation of Structured Reports for European Court of Human Rights Case Law

TL;DR

LexGenie introduces an automated LLM-based pipeline to generate structured, multi-case reports from European Court of Human Rights case law by topic. It combines keyphrase-based paragraph indexing, MMR-driven retrieval, BERTopic-HDBSCAN clustering, and iterative content generation to produce coherent outlines and subsections with citations from HUDOC. Expert and automated evaluations indicate strong structure and content quality, while ablations underscore the importance of keyphrase indexing, retrieval diversity, and reorganization for coherence. The work demonstrates scalable cross-case legal analysis and points to future extensions to additional jurisdictions and enhanced cross-sectional linking.

Abstract

Analyzing large volumes of case law to uncover evolving legal principles, across multiple cases, on a given topic is a demanding task for legal professionals. Structured topical reports provide an effective solution by summarizing key issues, principles, and judgments, enabling comprehensive legal analysis on a particular topic. While prior works have advanced query-based individual case summarization, none have extended to automatically generating multi-case structured reports. To address this, we introduce LexGenie, an automated LLM-based pipeline designed to create structured reports using the entire body of case law on user-specified topics within the European Court of Human Rights jurisdiction. LexGenie retrieves, clusters, and organizes relevant passages by topic to generate a structured outline and cohesive content for each section. Expert evaluation confirms LexGenie's utility in producing structured reports that enhance efficient, scalable legal analysis.

Paper Structure

This paper contains 18 sections, 7 figures, 3 tables.

Table of Contents

  1. Introduction
  2. LexGenie
  3. Approach
  4. Indexing Case law documents
  5. Structure Generation
  6. Content Generation
  7. User Interface
  8. Evaluation
  9. Report Structure
  10. Content Generation
  11. Qualitative Case Study
  12. Conclusion
  13. LexGenie Prompts
  14. Keyphrase Generation
  15. Prompt
  16. ...and 3 more sections

Figures (7)

  • Figure 1: Overview of our approach, LexGenie.
  • Figure 2: LexGenie interface. Given a legal topic as query, it automatically retrieves relevant documents and generates a table of content structure for the report. Finally, content for each sub-section in report is populated and the whole report is available for download.
  • Figure 3: Generating keyphrases from paragraphs of case law judgements.
  • Figure 4: Generating topic name for each cluster.
  • Figure 5: Organize topics into a hierarchical structure.
  • ...and 2 more figures