Robust and explainable Retrieval-Augmented Generation under retrieval noise

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 either over-trust incorrect context or underuse context when the user explicitly asks for context-following behavior. Therefore, we propose Intent-Guided Decoding (IGD), a framework that arbitrates between retrieved context and parametric memory according to user intent. IGD uses answer-level filtering and token-level correction to steer the final decoding trajectory between retrieved context and parametric memory. We evaluate IGD on three faithful QA benchmarks and three factual-conflict benchmarks across five LLMs, IGD substantially improves factual recovery, achieving gains of up to 65.4 percentage points on factual-conflict benchmarks over Direct RAG, while preserving or improving strict context-following behavior, this findings highlight the importance of balancing factuality and faithfulness in RAG.

Testing Retrieval-Augmented Generation Systems with Chunk Coverage

Chunk Coverage (CC), an oracle-independent test adequacy criterion for testing the retrieval component of RAG systems, is introduced and results show that CC captures retrieval diversity relevant to effective testing without requiring test oracles.

Does More Retrieved Evidence Help Visual Retrieval-Augmented Generation with Diffusion Language Models?

Visual retrieval-augmented generation (RAG) commonly expands the retrieved evidence set to improve answer-page coverage, implicitly assuming that all available evidence should be passed to the generator. We show that this assumption does not hold for diffusion language models (DLMs): retrieving more pages increases answer-page recall, whereas unconditionally passing all retrieved pages to the generator often reduces answer accuracy, primarily because of semantic conflict. A latent-source analysis explains this mismatch through source-coherence loss in parallel denoising, where position-wise proposals can combine incompatible visual sources into unsupported answers. We further find that such interference is already visible in the first-step answer-block distribution, making it possible to assess evidence before decoding. To preserve retrieval coverage while limiting harmful visual exposure, we propose the Entropy-Based Candidate Filter (ECF), a training-free evidence-admission framework. To reduce irrelevant content within individual candidates, ECF constructs multi-granularity evidence units; to identify beneficial additional evidence, it uses blank-controlled block confidence and retrieval rank to determine whether and which candidate should enter the final context. Across three multimodal DLMs and five visual QA benchmarks, ECF improves answer accuracy by 2.62 percentage points on average over the strongest fixed top-$k$ input and, with LLaDA2.0-Uni, by 2.37 percentage points on average over the best competing training-free result for each dataset. These results show that broader retrieval benefits visual DLM-RAG through selective evidence admission rather than unconditional evidence expansion. Code is publicly available at https://github.com/wjkuser/ECF.

Evaluating RAG approaches for Question Answering

A Reproducible and Budget-Aware Framework for Evaluating Local Retrieval-Augmented Generation (RAG) Robustness to Perturbations

The idea of context is no longer considered secondary in the construction of language-model systems. With the use of local Retrieval-Augmented Generation, even a tiny modification of the prompt or the context might produce another set of retrievals, citations, and ultimately different answers; however, in practice, tests are often performed with only one version of the question. In this work, we suggest a local context-engineering framework for exploring perturbation robustness, reproducibility, and budgetfriendly assessment in one unified pipeline. Local RAG is built on several small teaching packs for the models; perturbations are introduced to the queries, each experiment is recorded in capsule format, and a gate mechanism based on the decision tree is used to judge if the whole perturbation suite can be skipped, minimized, or run. As a result, the augmented capsule-derived data set contains 3,570 perturbation rows, out of which 2,619 labeled rows are used for retraining. In this labeled subset, BLEU scores are available in 446 cases, answer perplexity and semanticjudgment scores are available in 1,668 cases, citation overlap is available for all rows, and retrieval overlap is available for 2,099 rows. The final decision tree obtains 0.915 ROC-AUC, 0.891 PR-AUC, 0.913 accuracy, 0.863 F1 score, and expected savings of 76.5% on the held-out augmented test split. A more conservative threshold setting lowers the stable-risk value from 0.084 to 0.062, while reducing expected savings to 57.4%. Thus, we provide a local study pipeline to examine the effect of perturbations on answer stability, contradictions, robustness, and budget-friendly evaluation.

Exploring Internal Emphasis for Robust Noisy RAG