Debatrix: Multi-dimensional Debate Judge with Iterative Chronological Analysis Based on LLM
This addresses the problem of automated debate evaluation for researchers and practitioners, but it is incremental as it builds on existing LLM methods for a specific domain.
The paper tackles the challenge of automatically judging multi-turn debates by proposing Debatrix, a system that uses LLMs with iterative chronological analysis and multi-dimensional evaluation, showing a notable enhancement over directly using LLMs for debate evaluation.
How can we construct an automated debate judge to evaluate an extensive, vibrant, multi-turn debate? This task is challenging, as judging a debate involves grappling with lengthy texts, intricate argument relationships, and multi-dimensional assessments. At the same time, current research mainly focuses on short dialogues, rarely touching upon the evaluation of an entire debate. In this paper, by leveraging Large Language Models (LLMs), we propose Debatrix, which makes the analysis and assessment of multi-turn debates more aligned with majority preferences. Specifically, Debatrix features a vertical, iterative chronological analysis and a horizontal, multi-dimensional evaluation collaboration. To align with real-world debate scenarios, we introduced the PanelBench benchmark, comparing our system's performance to actual debate outcomes. The findings indicate a notable enhancement over directly using LLMs for debate evaluation. Source code and benchmark data are available online at https://github.com/ljcleo/debatrix .