@inproceedings{fadeeva-etal-2026-faithfulness,
    title = "Faithfulness-Aware Uncertainty Quantification for Fact-Checking the Output of Retrieval-Augmented Generation",
    author = "Fadeeva, Ekaterina  and
      Rubashevskii, Aleksandr  and
      Piatrashyn, Dzianis  and
      Vashurin, Roman  and
      Dhuliawala, Shehzaad  and
      Shelmanov, Artem  and
      Baldwin, Timothy  and
      Nakov, Preslav  and
      Sachan, Mrinmaya  and
      Panov, Maxim",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.338/",
    pages = "6814--6836",
    ISBN = "979-8-89176-395-1",
    abstract = "Large Language Models (LLMs) enhanced with knowledge retrieval, an approach known as Retrieval-Augmented Generation (RAG), have achieved strong performance in open-domain question answering. However, RAG remains prone to hallucinations: factually incorrect outputs may arise from inaccuracies in the model{'}s internal knowledge and the retrieved context. Existing approaches to mitigating hallucinations often conflate factuality with faithfulness to the retrieved evidence, incorrectly labeling factually correct statements as hallucinations if they are not explicitly supported by the retrieval. In this paper, we introduce FRANQ (Faithfulness-aware Retrieval-Augmented UNcertainty Quantification), a new method for hallucination detection in RAG outputs. FRANQ applies distinct uncertainty quantification techniques to estimate factuality, conditioning on whether a statement is faithful to the retrieved context. To evaluate FRANQ and competing uncertainty quantification methods, we construct a new long-form question answering dataset annotated for both factuality and faithfulness, combining automated labeling with manual validation of challenging cases. Extensive experiments across multiple datasets, tasks, and LLMs show that FRANQ achieves more accurate detection of factual errors in RAG-generated responses compared to existing uncertainty quantification and hallucination detection approaches."
}