A Survey on LLM-as-a-Judge

TL;DR

This survey reviews the emerging use of Large Language Models as evaluators, discussing strategies to improve their reliability, standardization, and applicability across diverse assessment scenarios.

Contribution

It provides a comprehensive overview of methods to enhance LLM-as-a-Judge systems, introduces a novel benchmark for reliability evaluation, and discusses practical deployment challenges.

Findings

Proposed methodologies for assessing LLM reliability.

Identified key challenges in standardization and bias mitigation.

Introduced a new benchmark for evaluating LLM-as-a-Judge systems.

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.