Exécution de notre outil de synthèse sur un nouvel article
Vérifiez l’article ci-dessous, puis lancez sa synthèse.
When Attention Escapes: Diagnosing and Mitigating Hallucination in Retrieval-Augmented Generation
Wencheng Su (Zhejiang University), Qinglong Wang, Zhongjie Ba (Zhejiang University), Zhixuan Chu (Zhejiang University), Zhenyu Zhong (Ant Group (China)), Liu Yan (Ant Group (China)), Kui Ren (Zhejiang University)
Résumé : Retrieval-Augmented Generation (RAG) mitigates hallucinations by grounding generation in retrieved evidence, yet failures persist when models underutilize the retrieved context.While prior work attributes this to conflicts between external context and internal parametric knowledge encoded in Feed-Forward Networks (FFNs), our empirical analyses reveal that FFNderived signals are unstable and insufficient for reliable diagnosis across diverse contexts.We therefore propose the Attention Escape Score (AES), a training-free diagnostic framework that provides a mechanistic lens on RAG hallucinations via dynamic attention routing failures.We models the failures as weakened Semantic Anchoring, increased Contextual Distraction, and heightened Generation Inertia, moving beyond static component-level analyses.Extensive experiments show that AES significantly outperforms state-of-the-art baselines with robust cross-model generalization.Furthermore, we introduce Pruning Escape Routes (PER), a lightweight inference-time intervention that suppresses hallucinations by attenuating identified escape pathways, achieving improved faithfulness with negligible degradation to complex reasoning and general capabilities.