@inproceedings{abdaljalil-etal-2025-safe,
    title = "{SAFE}: A Sparse Autoencoder-Based Framework for Robust Query Enrichment and Hallucination Mitigation in {LLM}s",
    author = "Abdaljalil, Samir  and
      Pallucchini, Filippo  and
      Seveso, Andrea  and
      Kurban, Hasan  and
      Mercorio, Fabio  and
      Serpedin, Erchin",
    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.496/",
    doi = "10.18653/v1/2025.findings-emnlp.496",
    pages = "9335--9346",
    ISBN = "979-8-89176-335-7",
    abstract = "Despite the state-of-the-art performance of Large Language Models (LLMs), these models often suffer from hallucinations, which can undermine their performance in critical applications. In this work, we propose SAFE, a novel framework for detecting and mitigating hallucinations by leveraging Sparse Autoencoders (SAEs). While hallucination detection techniques and SAEs have been explored independently, their synergistic application in a comprehensive system, particularly for hallucination-aware query enrichment, has not been fully investigated. To validate the effectiveness of SAFE, we evaluate it on two models with available SAEs across four diverse cross-domain datasets designed to assess hallucination problems. Empirical results demonstrate that SAFE consistently improves query generation accuracy and mitigates hallucinations across all datasets, achieving accuracy improvements of up to 29.45{\%}."
}