Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909335246864384 |
|---|---|
| author | Ye, Jiayi Wang, Yanbo Huang, Yue Chen, Dongping Zhang, Qihui Moniz, Nuno Gao, Tian Geyer, Werner Huang, Chao Chen, Pin-Yu Chawla, Nitesh V Zhang, Xiangliang |
| author_facet | Ye, Jiayi Wang, Yanbo Huang, Yue Chen, Dongping Zhang, Qihui Moniz, Nuno Gao, Tian Geyer, Werner Huang, Chao Chen, Pin-Yu Chawla, Nitesh V Zhang, Xiangliang |
| contents | LLM-as-a-Judge has been widely utilized as an evaluation method in various benchmarks and served as supervised rewards in model training. However, despite their excellence in many domains, potential issues are under-explored, undermining their reliability and the scope of their utility. Therefore, we identify 12 key potential biases and propose a new automated bias quantification framework-CALM-which systematically quantifies and analyzes each type of bias in LLM-as-a-Judge by using automated and principle-guided modification. Our experiments cover multiple popular language models, and the results indicate that while advanced models have achieved commendable overall performance, significant biases persist in certain specific tasks. Empirical results suggest that there remains room for improvement in the reliability of LLM-as-a-Judge. Moreover, we also discuss the explicit and implicit influence of these biases and give some suggestions for the reliable application of LLM-as-a-Judge. Our work highlights the need for stakeholders to address these issues and remind users to exercise caution in LLM-as-a-Judge applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_02736 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge Ye, Jiayi Wang, Yanbo Huang, Yue Chen, Dongping Zhang, Qihui Moniz, Nuno Gao, Tian Geyer, Werner Huang, Chao Chen, Pin-Yu Chawla, Nitesh V Zhang, Xiangliang Computation and Language Artificial Intelligence LLM-as-a-Judge has been widely utilized as an evaluation method in various benchmarks and served as supervised rewards in model training. However, despite their excellence in many domains, potential issues are under-explored, undermining their reliability and the scope of their utility. Therefore, we identify 12 key potential biases and propose a new automated bias quantification framework-CALM-which systematically quantifies and analyzes each type of bias in LLM-as-a-Judge by using automated and principle-guided modification. Our experiments cover multiple popular language models, and the results indicate that while advanced models have achieved commendable overall performance, significant biases persist in certain specific tasks. Empirical results suggest that there remains room for improvement in the reliability of LLM-as-a-Judge. Moreover, we also discuss the explicit and implicit influence of these biases and give some suggestions for the reliable application of LLM-as-a-Judge. Our work highlights the need for stakeholders to address these issues and remind users to exercise caution in LLM-as-a-Judge applications. |
| title | Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2410.02736 |