CLAIM: An Intent-Driven Multi-Agent Framework for Analyzing Manipulation in Courtroom Dialogues

TL;DR

This paper introduces CLAIM, a multi-agent framework for detecting and analyzing manipulation in courtroom dialogues, supported by a new annotated dataset, aiming to improve fairness and transparency in legal NLP applications.

Contribution

The paper presents CLAIM, a novel intent-driven multi-agent framework, and introduces LegalCon, a comprehensive dataset for manipulation detection in courtroom conversations.

Findings

CLAIM improves manipulation detection accuracy.

LegalCon dataset enables detailed analysis of manipulative techniques.

Framework enhances fairness in judicial decision-making.

Abstract

Courtrooms are places where lives are determined and fates are sealed, yet they are not impervious to manipulation. Strategic use of manipulation in legal jargon can sway the opinions of judges and affect the decisions. Despite the growing advancements in NLP, its application in detecting and analyzing manipulation within the legal domain remains largely unexplored. Our work addresses this gap by introducing LegalCon, a dataset of 1,063 annotated courtroom conversations labeled for manipulation detection, identification of primary manipulators, and classification of manipulative techniques, with a focus on long conversations. Furthermore, we propose CLAIM, a two-stage, Intent-driven Multi-agent framework designed to enhance manipulation analysis by enabling context-aware and informed decision-making. Our results highlight the potential of incorporating agentic frameworks to improve fairness and transparency in judicial processes. We hope that this contributes to the broader application of NLP in legal discourse analysis and the development of robust tools to support fairness in legal decision-making. Our code and data are available at https://github.com/Disha1001/CLAIM.