@inproceedings{kulkarni-etal-2025-evaluating,
    title = "Evaluating Evaluation Metrics {--} The Mirage of Hallucination Detection",
    author = "Kulkarni, Atharva  and
      Zhang, Yuan  and
      Moniz, Joel Ruben Antony  and
      Ge, Xiou  and
      Tseng, Bo-Hsiang  and
      Piraviperumal, Dhivya  and
      Swayamdipta, Swabha  and
      Yu, Hong",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.1035/",
    doi = "10.18653/v1/2025.findings-emnlp.1035",
    pages = "19013--19032",
    ISBN = "979-8-89176-335-7",
    abstract = "Hallucinations pose a significant obstacle to the reliability and widespread adoption of language models, yet their accurate measurement remains a persistent challenge. While many task- and domain-specific metrics have been proposed to assess faithfulness and factuality concerns, the robustness and generalization of these metrics are still untested. In this paper, we conduct a large-scale empirical evaluation of 6 diverse sets of hallucination detection metrics across 4 datasets, 37 language models from 5 families, and 5 decoding methods. Our extensive investigation reveals concerning gaps in current hallucination evaluation: metrics often fail to align with human judgments, take an overtly myopic view of the problem, and show inconsistent gains with parameter scaling. Encouragingly, LLM-based evaluation, particularly with GPT-4, yields the best overall results, and mode-seeking decoding methods seem to reduce hallucinations, especially in knowledge-grounded settings. These findings underscore the need for more robust metrics to understand and quantify hallucinations, and better strategies to mitigate them."
}