An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4

• URL: http://arxiv.org/abs/2403.02839v3
• Date: Tue, 05 Nov 2024 09:07:22 GMT
• Title: An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4
• Authors: Hui Huang, Yingqi Qu, Xingyuan Bu, Hongli Zhou, Jing Liu, Muyun Yang, Bing Xu, Tiejun Zhao,
• Abstract summary: Fine-tuned judge models are claimed to achieve comparable evaluation capability with GPT-4. We introduce a method, leveraging GPT-4 to compensate for the limitations and improve the fine-tuned judges. Experiment results show our method achieves accuracy on par with GPT-4 with only 50% of the API expense.
• Score: 29.93673872618022
• License:
• Abstract: Recently, there has been a growing trend of utilizing Large Language Model (LLM) to evaluate the quality of other LLMs. Many studies have employed proprietary close-sourced models, especially GPT-4, as the evaluator. Alternatively, other works have fine-tuned judge models based on open-source LLMs as the evaluator. While the fine-tuned judge models are claimed to achieve comparable evaluation capability with GPT-4, in this work, we conduct an empirical study of judge models. Our findings indicate that although the fine-tuned judge models achieve high performance on in-domain test sets, even surpassing GPT-4, they underperform GPT-4 across several dimensions, including generalizability, fairness, aspect-specific evaluation, and scalability. We also reveal that the fine-tuned judge model inherently operates as a task-specific classifier, consequently imposing the limitations. Finally, we introduce a integrated method, leveraging GPT-4 to compensate for the limitations and improve the fine-tuned judges. Experiment results show our method achieves accuracy on par with GPT-4 with only 50% of the API expense.

Related papers

• Direct Judgement Preference Optimization [66.83088028268318]
  We train large language models (LLMs) as generative judges to evaluate and critique other models' outputs. We employ three approaches to collect the preference pairs for different use cases, each aimed at improving our generative judge from a different perspective. Our model robustly counters inherent biases such as position and length bias, flexibly adapts to any evaluation protocol specified by practitioners, and provides helpful language feedback for improving downstream generator models.
  arXiv  Detail & Related papers  (2024-09-23T02:08:20Z)
• GroUSE: A Benchmark to Evaluate Evaluators in Grounded Question Answering [0.0]
  Retrieval-Augmented Generation (RAG) has emerged as a common paradigm to use Large Language Models (LLMs) alongside private and up-to-date knowledge bases. We address the challenges of using LLM-as-a-Judge when evaluating grounded answers generated by RAG systems.
  arXiv  Detail & Related papers  (2024-09-10T15:39:32Z)
• See What LLMs Cannot Answer: A Self-Challenge Framework for Uncovering LLM Weaknesses [51.975495361024606]
  We propose a Self-Challenge evaluation framework with human-in-the-loop. Starting from seed instances that GPT-4 fails to answer, we prompt GPT-4 to summarize error patterns that can be used to generate new instances. We then build a benchmark, SC-G4, consisting of 1,835 instances generated by GPT-4 using these patterns, with human-annotated gold responses.
  arXiv  Detail & Related papers  (2024-08-16T19:01:52Z)
• Are Large Language Models Strategic Decision Makers? A Study of Performance and Bias in Two-Player Non-Zero-Sum Games [56.70628673595041]
  Large Language Models (LLMs) have been increasingly used in real-world settings, yet their strategic decision-making abilities remain largely unexplored. This work investigates the performance and merits of LLMs in canonical game-theoretic two-player non-zero-sum games, Stag Hunt and Prisoner Dilemma. Our structured evaluation of GPT-3.5, GPT-4-Turbo, GPT-4o, and Llama-3-8B shows that these models, when making decisions in these games, are affected by at least one of the following systematic biases.
  arXiv  Detail & Related papers  (2024-07-05T12:30:02Z)
• RLAIF-V: Aligning MLLMs through Open-Source AI Feedback for Super GPT-4V Trustworthiness [94.03511733306296]
  We introduce RLAIF-V, a framework that aligns MLLMs in a fully open-source paradigm for super GPT-4V trustworthiness. RLAIF-V maximally exploits the open-source feedback from two perspectives, including high-quality feedback data and online feedback learning algorithm. Experiments show that RLAIF-V substantially enhances the trustworthiness of models without sacrificing performance on other tasks.
  arXiv  Detail & Related papers  (2024-05-27T14:37:01Z)
• Open Source Language Models Can Provide Feedback: Evaluating LLMs' Ability to Help Students Using GPT-4-As-A-Judge [4.981275578987307]
  Large language models (LLMs) have shown great potential for the automatic generation of feedback in a wide range of computing contexts. However, concerns have been voiced around the privacy and ethical implications of sending student work to proprietary models. This has sparked considerable interest in the use of open source LLMs in education, but the quality of the feedback that such open models can produce remains understudied.
  arXiv  Detail & Related papers  (2024-05-08T17:57:39Z)
• Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models [56.02275285521847]
  We propose to evaluate models using a Panel of LLm evaluators (PoLL) We find that using a PoLL composed of a larger number of smaller models outperforms a single large judge, exhibits less intra-model bias due to its composition of disjoint model families, and does so while being over seven times less expensive.
  arXiv  Detail & Related papers  (2024-04-29T15:33:23Z)
• Evaluation Metrics in the Era of GPT-4: Reliably Evaluating Large Language Models on Sequence to Sequence Tasks [9.801767683867125]
  We provide a preliminary and hybrid evaluation on three NLP benchmarks using both automatic and human evaluation. We find that ChatGPT consistently outperforms many other popular models according to human reviewers on the majority of metrics. We also find that human reviewers rate the gold reference as much worse than the best models' outputs, indicating the poor quality of many popular benchmarks.
  arXiv  Detail & Related papers  (2023-10-20T20:17:09Z)
• Split and Merge: Aligning Position Biases in Large Language Model based Evaluators [23.38206418382832]
  PORTIA is an alignment-based system designed to mimic human comparison strategies to calibrate position bias. Our results show that PORTIA markedly enhances the consistency rates for all the models and comparison forms tested. It rectifies around 80% of the position bias instances within the GPT-4 model, elevating its consistency rate up to 98%.
  arXiv  Detail & Related papers  (2023-09-29T14:38:58Z)
• Analyzing the Performance of GPT-3.5 and GPT-4 in Grammatical Error Correction [28.58384091374763]
  GPT-3 and GPT-4 models are powerful, achieving high performance on a variety of Natural Language Processing tasks. We perform experiments testing the capabilities of a GPT-3.5 model (text-davinci-003) and a GPT-4 model (gpt-4-0314) on major GEC benchmarks. We report the performance of our best prompt on the BEA-2019 and JFLEG datasets, finding that the GPT models can perform well in a sentence-level revision setting.
  arXiv  Detail & Related papers  (2023-03-25T03:08:49Z)
• GPT-4 Technical Report [116.90398195245983]
  GPT-4 is a large-scale, multimodal model which can accept image and text inputs and produce text outputs. It exhibits human-level performance on various professional and academic benchmarks, including passing a simulated bar exam with a score around the top 10% of test takers.
  arXiv  Detail & Related papers  (2023-03-15T17:15:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.