@inproceedings{fan-etal-2026-refl,
    title = "{R}e{FL}: Reflective Feedback Learning for Hallucination Detection of Large Language Models",
    author = "Fan, Cunhang  and
      Zhang, Jun  and
      Zhang, Xue  and
      Zhang, Shuai  and
      Lv, Zhao  and
      Tao, Jianhua  and
      Wen, Zhengqi",
    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.899/",
    pages = "19648--19665",
    ISBN = "979-8-89176-390-6",
    abstract = "Large Language Models (LLMs) often generate factually incorrect content, known as ``hallucinations'', which undermine the reliability and safety of their outputs. Existing hallucination detection methods either depend on external knowledge sources, incurring high computational costs and limiting real-time applicability, or extract the model{'}s internal states, leading to poor generalization. To address these issues, this paper proposes ReFL, a hallucination detection framework. ReFL leverages corrective in-context learning to dynamically guide LLMs to recognize their own prediction errors and adjust internal representations, critically without updating model weights. Specifically, by introducing a corrective in-context learning strategy, where triplets of input text, model prediction, and ground-truth label are embedded into the prompt to make the model explicitly aware of its own errors. The model reflects on prior outputs to adjust its internal states and generate semantically structured representations better aligned with factuality. This feedback mechanism encourages the model to shape a more coherent semantic space and enhances the LLM{'}s internal sensitivity to hallucinations. Experimental results on two benchmark datasets demonstrate that ReFL consistently outperforms existing methods, achieving state-of-the-art performance."
}