一个空间统治它们全部：联合缓解大语言模型中的事实性和忠实性幻觉
One SPACE to Rule Them All: Jointly Mitigating Factuality and Faithfulness Hallucinations in LLMs
AI总结：
SPACE通过联合编辑共享激活子空间，有效缓解大语言模型中的事实性和忠实性幻觉问题。
摘要：
大语言模型在自然语言处理中展现了前所未有的能力，但其实际部署仍受到持续的事实性和忠实性幻觉的阻碍。尽管现有方法分别处理这两种幻觉类型，但它们却无意中导致了性能权衡，因为针对一种类型的干预往往会加剧另一种。通过经验性和理论性地分析大语言模型中的激活空间动态，我们发现这些幻觉类别在神经表示中共享重叠的子空间，这为同时缓解提供了机会。为了利用这一见解，我们提出了SPACE，一个统一的框架，通过编辑共享的激活子空间来同时增强事实性和忠实性。SPACE通过双任务特征建模建立共享子空间存在的几何基础，然后通过结合谱聚类和注意力头显著性评分的混合探测策略来识别和编辑这些子空间。在多个基准数据集上的实验结果证明了我们方法的优越性。
英文摘要：
LLMs have demonstrated unprecedented capabilities in natural language processing, yet their practical deployment remains hindered by persistent factuality and faithfulness hallucinations. While existing methods address these hallucination types independently, they inadvertently induce performance trade-offs, as interventions targeting one type often exacerbate the other. Through empirical and theoretical analysis of activation space dynamics in LLMs, we reveal that these hallucination categories share overlapping subspaces within neural representations, presenting an opportunity for concurrent mitigation. To harness this insight, we propose SPACE, a unified framework that jointly enhances factuality and faithfulness by editing shared activation subspaces. SPACE establishes a geometric foundation for shared subspace existence through dual-task feature modeling, then identifies and edits these subspaces via a hybrid probe strategy combining spectral clustering and attention head saliency scoring. Experimental results across multiple benchmark datasets demonstrate the superiority of our approach.
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。
