Saved in:
Bibliographic Details
Main Authors: Lahiri, Sounak, Pai, Sumit, Weninger, Tim, Bhattacharya, Sanmitra
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.19164
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913891190046720
author Lahiri, Sounak
Pai, Sumit
Weninger, Tim
Bhattacharya, Sanmitra
author_facet Lahiri, Sounak
Pai, Sumit
Weninger, Tim
Bhattacharya, Sanmitra
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_19164
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning from Litigation: Graphs and LLMs for Retrieval and Reasoning in eDiscovery
Lahiri, Sounak
Pai, Sumit
Weninger, Tim
Bhattacharya, Sanmitra
Artificial Intelligence
Information Retrieval
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.
title Learning from Litigation: Graphs and LLMs for Retrieval and Reasoning in eDiscovery
topic Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2405.19164