@inproceedings{pradhan-todi-2023-understanding,
    title = "Understanding Large Language Model Based Metrics for Text Summarization",
    author = "Pradhan, Abhishek  and
      Todi, Ketan",
    editor = {Deutsch, Daniel  and
      Dror, Rotem  and
      Eger, Steffen  and
      Gao, Yang  and
      Leiter, Christoph  and
      Opitz, Juri  and
      R{\"u}ckl{\'e}, Andreas},
    booktitle = "Proceedings of the 4th Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2023",
    address = "Bali, Indonesia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2023.eval4nlp-1.12/",
    doi = "10.18653/v1/2023.eval4nlp-1.12",
    pages = "149--155",
    abstract = "This paper compares the two most widely used techniques for evaluating generative tasks with large language models (LLMs): prompt-based evaluation and log-likelihood evaluation as part of the Eval4NLP shared task. We focus on the summarization task and evaluate both small and large LLM models. We also study the impact of LLAMA and LLAMA 2 on summarization, using the same set of prompts and techniques. We used the Eval4NLP dataset for our comparison. This study provides evidence of the advantages of prompt-based evaluation techniques over log-likelihood based techniques, especially for large models and models with better reasoning power."
}