Courtroom-LLM: An Innovative Courtroom-Analogous Framework for Text Classification

Anonymous

Abstract: In this research, we introduce the Courtroom-LLM framework, a novel multi-LLM structure inspired by legal courtroom processes, aiming to enhance decision-making in ambiguous text classification scenarios. Our approach simulates a courtroom setting within LLMs, assigning roles similar to those of prosecutors, defense attorneys, and judges, to facilitate comprehensive analysis of complex textual cases. We demonstrate that this structured multi-LLM setup can significantly improve decision-making accuracy, particularly in ambiguous situations, by harnessing the synergistic effects of diverse LLM arguments. Our results from thorough evaluations on various NLP tasks show that the Courtroom-LLM framework surpasses both conventional single LLM classifiers and basic structured multi-LLM systems, underscoring the benefits of our legal proceedings-inspired model in enhancing NLP decision-making.

Paper Type: long

Research Area: NLP Applications

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Position papers

Languages Studied: English