paper-with-me

홈 › Papers

Neuro-RIT: Neuron-Guided Instruction Tuning for Robust Retrieval-Augmented Language Model

2026-04-02 · Jaemin Kim, Jae O Lee, Sumyeong Ahn, Seo Yeon Park arxiv

Retrieval-Augmented Language Models (RALMs) have demonstrated significant potential in knowledge-intensive tasks; however, they remain vulnerable to performance degradation when presented with irrelevant or noisy retrieved contexts. Existing approaches to enhance robustness typically operate via coarse-grained parameter updates at the layer or module level, often overlooking the inherent neuron-level sparsity of Large Language Models (LLMs). To address this limitation, we propose Neuro-RIT (Neuron-guided Robust Instruction Tuning), a novel framework that shifts the paradigm from dense adaptation to precision-driven neuron alignment. Our method explicitly disentangles neurons that are responsible for processing relevant versus irrelevant contexts using attribution-based neuron mining. Subsequently, we introduce a two-stage instruction tuning strategy that enforces a dual capability for noise robustness: achieving direct noise suppression by functionally deactivating neurons exclusive to irrelevant contexts, while simultaneously optimizing targeted layers for evidence distillation. Extensive experiments across diverse QA benchmarks demonstrate that Neuro-RIT consistently outperforms strong baselines and robustness-enhancing methods.

📄 PDF Abstract BibTeX arXiv:2604.02194

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

MNAFT: modality neuron-aware fine-tuning of multimodal large language models for image translation

2026-04-18 · Bo Li, Ningyuan Deng, Tianyu Dong, Shaobo Wang 외 arxiv

Multimodal large language models (MLLMs) have shown impressive capabilities, yet they often struggle to effectively capture the fine-grained textual information within images crucial for accurate image translation. This …

NeuroGenPoisoning: Neuron-Guided Attacks on Retrieval-Augmented Generation of LLM via Genetic Optimization of External Knowledge

2025-10-24 · Hanyu Zhu, Lance Fiondella, Jiawei Yuan, Kai Zeng 외 arxiv

Retrieval-Augmented Generation (RAG) empowers Large Language Models (LLMs) to dynamically integrate external knowledge during inference, improving their factual accuracy and adaptability. However, adversaries can inject …

NeuPAT: Neuron-aware Plasticity Allocation Tuning for Language-Preserving MLLMs

2026-08-08 · Jiayue Jin, Jingwei Zhang, Chen Wang, Jing Liu 외 hf

Multimodal expansion of large language models (LLMs) enables new perceptual capabilities but often compromises the language intelligence acquired during pretraining. In this work, we investigate this phenomenon from the …

Task-Specific Data Selection for Instruction Tuning via Monosemantic Neuronal Activations

2025-03-19 · Da Ma, Gonghu Shang, Zhi Chen, Libo Qin 외

Instruction tuning improves the ability of large language models (LLMs) to follow diverse human instructions, but achieving strong performance on specific target tasks remains challenging. A critical bottleneck is select…

Targeted Interpretable Safety Neuron Enhancement for Multilingual Vision-Language Large Models

2026-04-10 · Enyi Shi, Fei Shen, Shuyi Miao, Linxia Zhu 외 arxiv

With the widespread deployment of vision-language large models (VLLMs), their safety alignment faces dual challenges across languages and modalities. Existing methods model multilingual and multimodal safety separately, …