Debatrix: Multi-dimensional Debate Judge with Iterative Chronological Analysis Based on LLM
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917699233251328 |
|---|---|
| author | Liang, Jingcong Ye, Rong Han, Meng Lai, Ruofei Zhang, Xinyu Huang, Xuanjing Wei, Zhongyu |
| author_facet | Liang, Jingcong Ye, Rong Han, Meng Lai, Ruofei Zhang, Xinyu Huang, Xuanjing Wei, Zhongyu |
| contents | 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 . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_08010 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Debatrix: Multi-dimensional Debate Judge with Iterative Chronological Analysis Based on LLM Liang, Jingcong Ye, Rong Han, Meng Lai, Ruofei Zhang, Xinyu Huang, Xuanjing Wei, Zhongyu Computation and Language 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 . |
| title | Debatrix: Multi-dimensional Debate Judge with Iterative Chronological Analysis Based on LLM |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2403.08010 |