Exploring Internal Emphasis for Robust Noisy RAG

Open access Jul 2026

Robust and explainable Retrieval-Augmented Generation under retrieval noise

Testing how retrieval noise affects RAG and whether reranking, citation-aware generation, and lightweight verification can improve system behaviour suggests that robust and explainable RAG is a multi-objective problem.

Shirui Chen · Advances in Engineering Inno... · 0 citations

Book Open access Jul 2026

Incentivizing Retrieval-Augmented Generation via Inner Adaptive Context Selection

InnerRAG is a novel paradigm that empowers LLMs to autonomously select relevant context during generation by endowing the model to accurately identify the documents that are most helpful for generation from long contexts, leading to substantial improvements in generation quality while maintaining computational efficien...

Chenxu Cui, Lin Shen, Haihui Fan et al. · Annual International ACM SIG... · 0 citations

Book Open access Jul 2026

Latent Retrieval Augmented Generation

Latent RAG is introduced, a novel paradigm that performs knowledge injection entirely within the continuous latent space, and enables more natural knowledge integration while achieving 9,200X storage reduction compared to Parametric RAG.

Shuran Zhou, Junan Chen, Rui Ling et al. · Annual International ACM SIG... · 0 citations

Preprint Aug 2026

Better Retrieval, Worse Robustness: How Multi-hop RAG Amplifies Upstream ASR Errors

Speech-based applications pass spoken queries through automatic speech recognition (ASR) before any retrieval module, so ASR errors enter the pipeline as a fixed upstream constraint. We empirically test whether two extensions to standard retrieval-augmented generation (RAG), entity-graph linking and iterative reformula...

Zhenghua Bao · 1 citation

Preprint Aug 2026

When Context Misleads: Intent-Guided Decoding for Robust Retrieval-Augmented Generation

Retrieval-augmented generation (RAG) improves large language models by grounding generation in external evidence, but it also introduces a source trust problem: retrieved context may be useful, irrelevant, or even misleading. Existing RAG systems often apply a fixed trust policy toward retrieved evidence, which can eit...

Haolin Jin, Pengyue Yang, Hua-Min Chen · 0 citations

#artificial intelligence Preprint Aug 2026

Knowing Before Answering: Decoding Language Models for Reliable RAG

The results suggest that language models internally encode whether retrieved evidence is sufficient to support answering, and that this signal can be decoded reliably for RAG triage.

Syed Mahbubul Huq, Chris Child, Tillman Weyde et al. · 0 citations