@inproceedings{wu-etal-2025-meta,
    title = "Meta-Rewarding Language Models: Self-Improving Alignment with {LLM}-as-a-Meta-Judge",
    author = "Wu, Tianhao  and
      Yuan, Weizhe  and
      Golovneva, Olga  and
      Xu, Jing  and
      Tian, Yuandong  and
      Jiao, Jiantao  and
      Weston, Jason E  and
      Sukhbaatar, Sainbayar",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.583/",
    pages = "11548--11565",
    ISBN = "979-8-89176-332-6",
    abstract = "Large Language Models (LLMs) are rapidly surpassing human knowledge in many domains. While improving these models traditionally relies on costly human data, recent self-rewarding mechanisms have shown that LLMs can improve by judging their own responses instead of relying on human labelers. However, existing methods have primarily focused on improving model responses rather than judgment capabilities, resulting in rapid saturation during iterative training. To address this issue, we introduce a novel Meta-Rewarding step to the self-improvement process, where the model judges its own judgements and uses that feedback to refine its judgment skills. Surprisingly, this unsupervised approach improves the model{'}s ability to judge and follow instructions, as demonstrated by a win rate improvement of Llama-3-8B-Instruct from 22.9{\%} to 39.4{\%} on AlpacaEval 2, and 20.6{\%} to 29.1{\%} on Arena-Hard. These results strongly suggest the potential for self-improving models without human supervision."
}