Research
SCoNE: Selective Context-aware Neuron Editing for Robust Retrieval-Augmented Generation
arXiv:2609.00689v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) is highly sensitive to retrieval noise: when retrieved documents mix informative and irrelevant context, LLMs are e
arXiv:2609.00689v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) is highly sensitive to retrieval noise: when retrieved documents mix informative and irrelevant context, LLMs are easily distracted, leading to hallucinations. To overcome this, we propose SCoNE (Selective Context-aware Neuron Editing), a training-free model editing approach that improves retrieval noise robustness by selectively strengthening context-aware FFN neurons that are identified by both high attribution and high cross-input variability. SCoNE requires only a small number of mining samples, no fine-tuning, and no inference-time overhead. Across various knowledge-intensive question-answering benchmarks and two LLM backbones, SCoNE consistently outperforms competitive baseline methods. Our code is available at https://github.com/HYU-ARK-Lab/SCoNE.
Related
- No-Worse Context-Aware Decoding: Preventing Neutral Regression in Context-Conditioned Generation
- How Retrieved Context Shapes Internal Representations in RAG
- Learning to Erase Private Knowledge from Multi-Documents for Retrieval-Augmented Large Language Models
- TRIS: A Tri-Layer Retrieval Integrity Sieve Against Knowledge Poisoning
Source: arXiv cs.CL | 2026-09-02