DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations

Aryo Pradipta Gema, Chen Jin, Ahmed Abdulaal, Tom Diethe, Philip Alexander Teare, Beatrice Alex, Pasquale Minervini, Amrutha Saseendran

Keywords: Large Language Models, Hallucination, Constrained Decoding, Retrieval Heads

TL;DR: We propose DeCoRe, a training-free method that reduces hallucinations in LLMs by contrasting outputs from the base model and a masked version without retrieval heads, using predictive entropy to reject unfaithful responses.

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 significantly 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 by 2.4\% and NQ-Swap by 5.5\%).

Primary Area: generative models

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 7627