paper-with-me

홈 › Papers

Leveraging LLMs as Meta-Judges: A Multi-Agent Framework for Evaluating LLM Judgments

2025-04-23 · Yuran Li, Jama Hussein Mohamud, Chongren Sun, Di wu, Benoit Boulet

Large language models (LLMs) are being widely applied across various fields, but as tasks become more complex, evaluating their responses is increasingly challenging. Compared to human evaluators, the use of LLMs to support performance evaluation offers a more efficient alternative. However, most studies focus mainly on aligning LLMs' judgments with human preferences, overlooking the existence of biases and mistakes in human judgment. Furthermore, how to select suitable LLM judgments given multiple potential LLM responses remains underexplored. To address these two aforementioned issues, we propose a three-stage meta-judge selection pipeline: 1) developing a comprehensive rubric with GPT-4 and human experts, 2) using three advanced LLM agents to score judgments, and 3) applying a threshold to filter out low-scoring judgments. Compared to methods using a single LLM as both judge and meta-judge, our pipeline introduces multi-agent collaboration and a more comprehensive rubric. Experimental results on the JudgeBench dataset show about 15.55\% improvement compared to raw judgments and about 8.37\% improvement over the single-agent baseline. Our work demonstrates the potential of LLMs as meta-judges and lays the foundation for future research on constructing preference datasets for LLM-as-a-judge reinforcement learning.

📄 PDF Abstract BibTeX arXiv:2504.17087

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Adam 설명 없음
Multi-Head Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?

2026-05-18 · Leyao Wang, Yanan He, Peng Chen, Asaf Yehudai 외 arxiv

Deep research agents increasingly automate complex information-seeking tasks, producing evidence-grounded reports via multi-step reasoning, tool use, and synthesis. Their growing role demands scalable, reliable evaluatio…

LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods

2024-12-07 · Haitao Li, Qian Dong, Junjie Chen, Huixue Su 외

The rapid advancement of Large Language Models (LLMs) has driven their expanding application across various fields. One of the most promising applications is their role as evaluators based on natural language responses, …

When AIs Judge AIs: The Rise of Agent-as-a-Judge Evaluation for LLMs

2025-08-05 · Fangyi Yu arxiv

As large language models (LLMs) grow in capability and autonomy, evaluating their outputs-especially in open-ended and complex tasks-has become a critical bottleneck. A new paradigm is emerging: using AI agents as the ev…

Conversation for Non-verifiable Learning: Self-Evolving LLMs through Meta-Evaluation

2026-01-29 · Yuan Sui, Bryan Hooi arxiv

Training large language models (LLMs) for non-verifiable tasks, such as creative writing, dialogue, and ethical reasoning, remains challenging due to the absence of ground-truth labels. While LLM-as-Judge approaches offe…

ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning

2025-03-12 · Ziyu Wan, Yunxiang Li, Xiaoyu Wen, Yan Song 외

Recent research on Reasoning of Large Language Models (LLMs) has sought to further enhance their performance by integrating meta-thinking -- enabling models to monitor, evaluate, and control their reasoning processes for…

Multi-agent Reinforcement Learningreinforcement-learningReinforcement Learning