SAFE: A Sparse Autoencoder-Based Framework for Robust Query Enrichment and Hallucination Mitigation in LLMs

Samir Abdaljalil, Filippo Pallucchini, Andrea Seveso, Hasan Kurban, Fabio Mercorio, Erchin Serpedin


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%.
Anthology ID:
2025.findings-emnlp.496
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9335–9346
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.496/
DOI:
Bibkey:
Cite (ACL):
Samir Abdaljalil, Filippo Pallucchini, Andrea Seveso, Hasan Kurban, Fabio Mercorio, and Erchin Serpedin. 2025. SAFE: A Sparse Autoencoder-Based Framework for Robust Query Enrichment and Hallucination Mitigation in LLMs. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 9335–9346, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
SAFE: A Sparse Autoencoder-Based Framework for Robust Query Enrichment and Hallucination Mitigation in LLMs (Abdaljalil et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.496.pdf
Checklist:
 2025.findings-emnlp.496.checklist.pdf