mlsanityData to 14 Oct 2026

SCoNE: Selective Context-aware Neuron Editing for Robust Retrieval-Augmented Generation

arXiv 2609.00689 ↗First posted 1 Sep 2026cs.CLcited by 0

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 26 of its 38 references that are in the map. First posted on arXiv 1 Sep 2026.

Builds on

26 of 38 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 25

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,886
  3. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,100
  4. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  5. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  6. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
  7. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  8. 2022Locating and Editing Factual Associations in GPTcited by 2,691
  9. 2020Transformer Feed-Forward Layers Are Key-Value Memoriescited by 1,336
  10. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  11. 2022Mass-Editing Memory in a Transformercited by 1,001
  12. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
13 more
  1. 2017Crowdsourcing Multiple Choice Science Questionscited by 765
  2. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 573
  3. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 369
  4. 2023Trusting Your Evidence: Hallucinate Less with Context-aware Decodingcited by 327
  5. 2024The Power of Noise: Redefining Retrieval for RAG Systemscited by 281
  6. 2022ASQA: Factoid Questions Meet Long-Form Answerscited by 234
  7. 2024SPLADE-v3: New baselines for SPLADEcited by 72
  8. 2024IRCAN: Mitigating Knowledge Conflicts in LLM Generation via Identifying and Reweighting Context-Aware Neuronscited by 38
  9. 2024PA-RAG: RAG Alignment via Multi-Perspective Preference Optimizationcited by 11
  10. 2025HyperRAG: Enhancing Quality-Efficiency Tradeoffs in Retrieval-Augmented Generation with Reranker KV-Cache Reusecited by 8
  11. 2025iQUEST: An Iterative Question-Guided Framework for Knowledge Base Question Answeringcited by 8
  12. 2025Sentinel: Decoding Context Utilization via Attention Probing for Efficient LLM Context Compressioncited by 4
  13. 2025Learning to Extract Rational Evidence via Reinforcement Learning for Retrieval-Augmented Generationcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Where Does Robustness Live? Neuron-Guided Adaptation for Retrieval-Augmented Language Models
  2. 2024Prompt Perturbation in Retrieval-Augmented Generation based Large Language Models
  3. 2024Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Training
  4. 2026SHIFT: Gate-Modulated Activation Steering for Knowledge Conflict Mitigation in Retrieval-Augmented Generation
  5. 2026Tackling the Inherent Difficulty of Noise Filtering in RAG
  6. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers
  7. 2024Leveraging the Domain Adaptation of Retrieval Augmented Generation Models for Question Answering and Reducing Hallucination
  8. 2026Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation