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

arXiv: https://arxiv.org/abs/2506.04131 · HTML: https://mlsanity.com/paper/2506.04131/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 32 references that are in the map.
- First posted on arXiv 4 Jun 2025.

## Builds on (most cited first, 7 of 7)

- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [ToMBench: Benchmarking Theory of Mind in Large Language Models](https://mlsanity.com/paper/2402.15052/) (2024)
- [MentalManip: A Dataset For Fine-grained Analysis of Mental Manipulation in Conversations](https://mlsanity.com/paper/2405.16584/) (2024)
- [Human Decision-making is Susceptible to AI-driven Manipulation](https://mlsanity.com/paper/2502.07663/) (2025)
- [Detecting Conversational Mental Manipulation with Intent-Aware Prompting](https://mlsanity.com/paper/2412.08414/) (2024)
- [Enhanced Detection of Conversational Mental Manipulation Through Advanced Prompting Techniques](https://mlsanity.com/paper/2408.07676/) (2024)
- [Communication is All You Need: Persuasion Dataset Construction via Multi-LLM Communication](https://mlsanity.com/paper/2502.08896/) (2025)

## Built on by (most cited first, 1 of 1)

- [The Hidden Puppet Master: Predicting Human Belief Change in Manipulative LLM Dialogues](https://mlsanity.com/paper/2603.20907/) (2026)

## Abstract (arXiv)

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.