@inproceedings{qin-etal-2025-learning,
    title = "Learning Auxiliary Tasks Improves Reference-Free Hallucination Detection in Open-Domain Long-Form Generation",
    author = "Qin, Chengwei  and
      Zhou, Wenxuan  and
      Sankararaman, Karthik Abinav  and
      Wang, Nanshu  and
      Xu, Tengyu  and
      Radovic, Alexander  and
      Helenowski, Eryk  and
      Talebzadeh, Arya  and
      Tayade, Aditya  and
      Wang, Sinong  and
      Joty, Shafiq  and
      Fang, Han  and
      Ma, Hao",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.acl-short.93/",
    pages = "1173--1182",
    ISBN = "979-8-89176-252-7",
    abstract = "Hallucination, the generation of factually incorrect information, remains a significant challenge for large language models (LLMs), especially in open-domain long-form generation. Existing approaches for detecting hallucination in long-form tasks either focus on limited domains or rely heavily on external fact-checking tools, which may not always be available.In this work, we systematically investigate reference-free hallucination detection in open-domain long-form responses. Our findings reveal that internal states (e.g., model{'}s output probability and entropy) alone are insufficient for reliably (i.e., better than random guessing) distinguishing between factual and hallucinated content. To enhance detection, we explore various existing approaches, including prompting-based methods, probing, and fine-tuning, with fine-tuning proving the most effective. To further improve the accuracy, we introduce a new paradigm, named RATE-FT, that augments fine-tuning with an auxiliary task for the model to jointly learn with the main task of hallucination detection. With extensive experiments and analysis using a variety of model families {\&} datasets, we demonstrate the effectiveness and generalizability of our method, e.g., +3{\%} over general fine-tuning methods on LongFact."
}