ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate

Chi-Min Chan, Weize Chen, Yusheng Su, Jianxuan Yu, Wei Xue +3 more
2/12/2026

No official code found. Best implementation: thunlp/ChatEval (331 stars, Apache-2.0, last commit 2024-10-19).

Semantic Scholar

Code Implementations(1)

thunlp/ChatEvalCommunity64%
Apache-2.0

Codes for our paper "ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate"

33131Shell, PythonJul 18, 20232 years agoApache-2.0

Cite this paper

@article{chan2026chateval,
  title  = {ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate},
  author = {Chi-Min Chan and Weize Chen and Yusheng Su and Jianxuan Yu and Wei Xue and Shanghang Zhang and Jie Fu and Zhiyuan Liu},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:f6550f19338da79b558324117afe0b8c921e11d3},
  journal = {ICLR 2024 2024}
}

Discussion