@inproceedings{wu-etal-2024-instructeval,
    title = "{I}nstruct{E}val: Instruction-Tuned Text Evaluator from Human Preference",
    author = "Wu, Wenhao  and
      Li, Wei  and
      Xiao, Xinyan  and
      Liu, Jiachen  and
      Li, Sujian",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.findings-acl.799/",
    doi = "10.18653/v1/2024.findings-acl.799",
    pages = "13462--13474",
    abstract = "This paper explores to construct a general text evaluator based on open-source Large Language Models (LLMs), a domain predominantly occupied by commercial counterparts such as GPT-4. Recognizing the limitations of open-source models like Llama in evaluative tasks, we introduce InstructEval, a general multi-aspect text evaluator developed through instruction tuning of open-source LLMs. To overcome the shortage of annotated resources for multi-aspect evaluations, InstructEval combines extensive open Human Preference Modeling (HPM) datasets with a small set of multi-aspect annotated data.This approach not only enhances effectiveness in overall evaluation tasks but also exhibits improved performance in multi-aspect evaluation tasks.As demonstrated by our extensive experiments, InstructEval achieves comparable or superior performance to commercial LLMs like ChatGPT or GPT-4 in terms of both overall and multi-aspect evaluation."
}