Courtroom-LLM: A Legal-Inspired Multi-LLM Framework for Resolving Ambiguous Text Classifications

Sangkeun Jung, Jeesu Jung


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 evaluations across various text classification tasks show that the Courtroom-LLM framework outperforms both traditional single-LLM classifiers and simpler multi-LLM setups. These results highlight the advantages of our legal-inspired model in improving decision-making for text classification.
Anthology ID:
2025.coling-main.493
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7367–7385
Language:
URL:
https://aclanthology.org/2025.coling-main.493/
DOI:
Bibkey:
Cite (ACL):
Sangkeun Jung and Jeesu Jung. 2025. Courtroom-LLM: A Legal-Inspired Multi-LLM Framework for Resolving Ambiguous Text Classifications. In Proceedings of the 31st International Conference on Computational Linguistics, pages 7367–7385, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
Courtroom-LLM: A Legal-Inspired Multi-LLM Framework for Resolving Ambiguous Text Classifications (Jung & Jung, COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.493.pdf