Learning from Litigation: Graphs and LLMs for Retrieval and Reasoning in eDiscovery

Sounak Lahiri, Sumit Pai, Tim Weninger, Sanmitra Bhattacharya
5/29/2024
cs.AIcs.IR

No confident code implementation found for this paper.

Abstract

Electronic Discovery (eDiscovery) requires identifying relevant documents from vast collections for legal production requests. While artificial intelligence (AI) and natural language processing (NLP) have improved document review efficiency, current methods still struggle with legal entities, citations, and complex legal artifacts. To address these challenges, we introduce DISCOvery Graph (DISCOG), an emerging system that integrates knowledge graphs for enhanced document ranking and classification, augmented by LLM-driven reasoning. DISCOG outperforms strong baselines in F1-score, precision, and recall across both balanced and imbalanced datasets. In real-world deployments, it has reduced litigation-related document review costs by approximately 98\%, demonstrating significant business impact.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

ReLeVAnT: Relevance Lexical Vectors for Accurate Legal Text Classification

84% match2026

LegalGraphRAG: Multi-Agent Graph Retrieval-Augmented Generation for Reliable Legal Reasoning

83% match1 repo592026

Towards Supporting Legal Argumentation with NLP: Is More Data Really All You Need?

82% match2024

Bridging Legal Knowledge and AI: Retrieval-Augmented Generation with Vector Stores, Knowledge Graphs, and Hierarchical Non-negative Matrix Factorization

82% match1 repo262025

Constructing a Knowledge Graph for Vietnamese Legal Cases with Heterogeneous Graphs

81% match2023

Automatic Knowledge Graph Construction for Judicial Cases

81% match2024

Cite this paper

@article{lahiri2024learning,
  title  = {Learning from Litigation: Graphs and LLMs for Retrieval and Reasoning in eDiscovery},
  author = {Sounak Lahiri and Sumit Pai and Tim Weninger and Sanmitra Bhattacharya},
  year   = {2024},
  eprint = {2405.19164},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2405.19164v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2405.19164.svg)](https://codeofpaper.com/paper/2405.19164)

Discussion