SAFE：一种用于大型语言模型鲁棒查询增强与幻觉缓解的稀疏自编码器框架
SAFE: A Sparse Autoencoder-Based Framework for Robust Query Enrichment and Hallucination Mitigation in LLMs
AI总结：
本文提出SAFE框架，利用稀疏自编码器检测和缓解大型语言模型的幻觉，通过幻觉感知的查询增强提升性能，在多数据集上准确率提升达29.45%。
摘要：
尽管大型语言模型（LLMs）具有最先进的性能，但这些模型常出现幻觉，可能削弱其在关键应用中的表现。在本研究中，我们提出SAFE，一种通过利用稀疏自编码器（SAEs）来检测和缓解幻觉的新方法。尽管幻觉检测技术与SAEs已被独立探索，但它们在一个综合系统中的协同应用，特别是用于幻觉感知的查询增强，尚未得到充分研究。为验证SAFE的有效性，我们在具有可用SAEs的两个模型上，跨三个旨在评估幻觉问题的多样化跨领域数据集对其进行了评估。实证结果表明，SAFE在所有数据集上持续提升查询生成准确率并缓解幻觉，实现了高达29.45%的准确率提升。
英文摘要：
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 method 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 three 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%.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
