LegalCon and CLAIM introduce a courtroom dialogue dataset and a two-stage multi-agent framework that reports improved manipulation detection and manipulator identification over zero-shot and few-shot LLM baselines.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CLAIM: An Intent-Driven Multi-Agent Framework for Analyzing Manipulation in Courtroom Dialogues
LegalCon and CLAIM introduce a courtroom dialogue dataset and a two-stage multi-agent framework that reports improved manipulation detection and manipulator identification over zero-shot and few-shot LLM baselines.