@inproceedings{chen-etal-2026-multi,
    title = "Multi-Agent-as-Judge: Aligning {LLM}-Agent-Based Automated Evaluation with Multi-Dimensional Human Evaluation",
    author = "Chen, Jiaju  and
      Lu, Yuxuan  and
      Wang, Xiaojie  and
      Zeng, Huimin  and
      Huang, Jing  and
      Gesi, Jiri  and
      Xu, Ying  and
      Yao, Bingsheng  and
      Wang, Dakuo",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.790/",
    pages = "17389--17416",
    ISBN = "979-8-89176-390-6",
    abstract = "Nearly all human work is collaborative; thus, the evaluation of real-world NLP applications often requires multiple dimensions that align with diverse human perspectives. As real human evaluator resources are often scarce and costly, the emerging ``LLM-as-a-judge'' paradigm sheds light on a promising approach to leverage LLM agents to believably simulate human evaluators. Yet, to date, existing LLM-as-a-judge approaches face two limitations: persona descriptions of agents are often arbitrarily designed, and the frameworks are not generalizable to other tasks. To address these challenges, we propose MAJ-EVAL, a Multi-Agent-as-Judge evaluation framework that can automatically construct multiple evaluator personas with distinct dimensions from relevant text documents (e.g., research papers), instantiate LLM agents with the personas, and engage in-group debates with multi-agents to generate multi-dimensional feedback. Our evaluation experiments in both the educational and medical domains demonstrate that MAJ-EVAL can generate evaluation results that better align with human experts' ratings compared with conventional automated evaluation metrics and existing LLM-as-a-judge methods."
}