A Survey on LLM-as-a-Judge

A comprehensive survey on LLM-as-a-Judge, submitted to arXiv on 23 Nov 2024 and revised through v6 on 19 Oct 2025, addresses how to build reliable LLM-based evaluation systems, proposing strategies to improve consistency, mitigate biases, and adapt to diverse scenarios, along with a novel benchmark for assessing reliability. The paper, authored by Xuhui Jiang and colleagues, serves as a foundational reference for researchers and practitioners in the rapidly evolving field.

Computer Science Computation and Language Submitted on 23 Nov 2024 v1 https://arxiv.org/abs/2411.15594v1 , last revised 19 Oct 2025 this version, v6 Title:A Survey on LLM-as-a-Judge View PDF /pdf/2411.15594 HTML experimental https://arxiv.org/html/2411.15594v6 Abstract:Accurate and consistent evaluation is crucial for decision-making across numerous fields, yet it remains a challenging task due to inherent subjectivity, variability, and scale. Large Language Models LLMs have achieved remarkable success across diverse domains, leading to the emergence of "LLM-as-a-Judge," where LLMs are employed as evaluators for complex tasks. With their ability to process diverse data types and provide scalable, cost-effective, and consistent assessments, LLMs present a compelling alternative to traditional expert-driven evaluations. However, ensuring the reliability of LLM-as-a-Judge systems remains a significant challenge that requires careful design and standardization. This paper provides a comprehensive survey of LLM-as-a-Judge, addressing the core question: How can reliable LLM-as-a-Judge systems be built? We explore strategies to enhance reliability, including improving consistency, mitigating biases, and adapting to diverse assessment scenarios. Additionally, we propose methodologies for evaluating the reliability of LLM-as-a-Judge systems, supported by a novel benchmark designed for this purpose. To advance the development and real-world deployment of LLM-as-a-Judge systems, we also discussed practical applications, challenges, and future directions. This survey serves as a foundational reference for researchers and practitioners in this rapidly evolving field. Submission history From: Xuhui Jiang view email /show-email/deaaef6f/2411.15594 Sat, 23 Nov 2024 16:03:35 UTC 1,888 KB v1 /abs/2411.15594v1 Mon, 16 Dec 2024 15:00:53 UTC 2,820 KB v2 /abs/2411.15594v2 Thu, 9 Jan 2025 03:08:17 UTC 1,477 KB v3 /abs/2411.15594v3 Sat, 1 Feb 2025 08:55:51 UTC 10,153 KB v4 /abs/2411.15594v4 Sun, 9 Mar 2025 05:21:22 UTC 13,276 KB v5 /abs/2411.15594v5 v6 Sun, 19 Oct 2025 10:32:43 UTC 26,593 KB References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs https://info.arxiv.org/labs/index.html .