JudgeLM: Fine-tuned Large Language Models are Scalable Judges

By Lianghui Zhu, Xinggang Wang, Xinlong Wang. International Conference on Learning Representations, 2023

381 citations recorded by the source corpus.

Evaluating Large Language Models (LLMs) in open-ended scenarios is challenging because existing benchmarks and metrics can not measure them comprehensively. To address this problem, we propose to fine-tune LLMs as scalable judges (JudgeLM) to evaluate LLMs efficiently and effectively in open-ended benchmarks. We first propose a comprehensive, large-scale, high-quality dataset containing task seeds, LLMs-generated answers, and GPT-4-generated judgments for fine-tuning high-performance judges, as well as a new benchmark for evaluating the judges. We train JudgeLM at different scales from 7B, 13B, to 33B parameters, and conduct a systematic analysis of its capabilities and behaviors. We then analyze the key biases in fine-tuning LLM as a judge and consider them as position bias, knowledge bias, and format bias. To address these issues, JudgeLM introduces a bag of techniques including swap augmentation, reference support, and reference drop, which clearly enhance the judge's performance. JudgeLM obtains the state-of-the-art judge performance on both the existing PandaLM benchmark and our proposed new benchmark. Our JudgeLM is efficient and the JudgeLM-7B only needs 3 minutes to judge 5K samples with 8 A100 GPUs. JudgeLM obtains high agreement with the teacher judge, achieving an agreement exceeding 90% that even surpasses human-to-human agreement. JudgeLM also demonstrates extended capabilities in being judges of the single answer, multimodal models, multiple answers, multi-turn chat, etc. Code is available at https://github.com/baaivision/JudgeLM.

View Paper: https://www.semanticscholar.org/paper/69ecf88a0d9752db7dc32b4917ee24b4974cea18

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge (2024, unknown): “For pointwise data, they adopt a “divide-and-conquer” strategy, where two critiques are collected from GPT-4 for a single response, combined into (2023) introduce JudgeLM and propose a comprehensive, large-scale, high-quality dataset containing task seeds, LLMs-generated answers, and…”
Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models (2024, methodology): “Reference-based Scoring In other cases, the model is provided with some ’gold’ reference r , which contains the information that should be included in a (e.g. (Zhu et al., 2023)).”
Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models (2024, background): “To address these issues, recent works have focused on developing evaluator LMs that are open-access, transparent, and controllable (Kim et al., 2023; Wang et al., 2023a,b; Li et al., 2023a; Zhu et al., 2023; Jiang et al., 2023b,c; Lee et al., 2024).”
Better Instruction-Following Through Minimum Bayes Risk (2024, unknown): “Follow-up works suggest that training on the evaluation traces of strong models may equip smaller models with strong evaluation capabilities (Kim et al., 2023; 2024; Zhu et al., 2023b; Vu et al., 2024; Wang et al., 2024b).”