@inproceedings{gema-etal-2025-decore,
    title = "{D}e{C}o{R}e: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations",
    author = "Gema, Aryo Pradipta  and
      Jin, Chen  and
      Abdulaal, Ahmed  and
      Diethe, Tom  and
      Teare, Philip Alexander  and
      Alex, Beatrice  and
      Minervini, Pasquale  and
      Saseendran, Amrutha",
    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.531/",
    doi = "10.18653/v1/2025.findings-emnlp.531",
    pages = "10003--10039",
    ISBN = "979-8-89176-335-7",
    abstract = "Large Language Models (LLMs) often hallucinate, producing unfaithful or factually incorrect outputs by misrepresenting the provided context or incorrectly recalling internal knowledge. Recent studies have identified specific attention heads within the Transformer architecture, known as retrieval heads, responsible for extracting relevant contextual information. We hypothesise that masking these retrieval heads can induce hallucinations and that contrasting the outputs of the base LLM and the masked LLM can reduce hallucinations. To this end, we propose Decoding by Contrasting Retrieval Heads (DeCoRe), a novel training-free decoding strategy that amplifies information found in the context and model parameters. DeCoRe mitigates potentially hallucinated responses by dynamically contrasting the outputs of the base LLM and the masked LLM, using conditional entropy as a guide. Our extensive experiments confirm that DeCoRe improves performance on tasks requiring high contextual faithfulness, such as summarisation (XSum by 18.6{\%}), instruction following (MemoTrap by 10.9{\%}), and open-book question answering (NQ-Open by 2.4{\%} and NQ-Swap by 5.5{\%})."
}