arXiv AI
A Hierarchical Consistency Framework for Auditing Retrieval-Augmented Generation Systems
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 1
Detecting and Repairing Hallucinations in Retrieval-Augmented Generation
arXiv:2608.29307v1 Announce Type: cross Abstract: Language models increasingly answer questions by consulting retrieved documents rather than memory alone, a design now common in search assistants an...
arXiv Computation and Language
Aug 27
ReliableRAG: Combating Misinformation in Retrieval-Augmented Generation via Reliability-Guided Reasoning Chains
ReliableRAG is a new framework for Retrieval-Augmented Generation that tackles misinformation in multi‑hop question answering. It extracts structured triples from retrieved documents, evaluates each triple’s reliability by combining semantic relevance to the query with credibility, and keeps only the top‑K reliable, non‑redundant triples. Using these refined triples, the system builds robust reasoning chains that filter out deceptive misinformation and produce accurate, trustworthy answers.
arXiv AI
Jun 30
A Systems-Level Analysis of Sensitivity, Robustness, and Stability in Retrieval-Augmented Generation
arXiv:2606. 28337v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems are often evaluated using final answer accuracy, even though their failures can originate from preprocessing, retrieval, context packing, or generation.
arXiv Computation and Language
Aug 28
Assessing the Downstream Utility of Evidence-Aware Retrieval in RAG
The paper investigates whether incorporating an evidence-support signal into retrieval evaluation for retrieval‑augmented generation (RAG) improves downstream decision‑making. Across multiple benchmarks and a TREC RAG 2025 setting, the evidence signal alters retriever rankings but its benefits vary: it does not consistently enhance retriever training, its usefulness for system selection depends on generator instructions, and it does not reliably predict answer quality on unseen topics. Human filtering of evidence‑rich passages preserves useful content, yet evaluators disagree on whether this improves final answers, indicating that evidence‑aware evaluation alone does not guarantee better downstream outcomes.
arXiv Computation and Language
Aug 25
Same Agent, Different Answers: A Repeat-Aware Audit of Corpus-Induced Answer Churn in Retrieval-Augmented QA
arXiv:2608.22856v1 Announce Type: cross Abstract: A retrieval-augmented QA system can return different answers after an index expansion even when its requested model identifier, prompt, retrieval pol...
arXiv AI
Aug 24
EnSI-RAG: Entity-Structure-Indexed Retrieval-Augmented Generation for Long-Document Question Answering
arXiv:2608.21252v1 Announce Type: cross Abstract: Question answering (QA) over long, connected documents remains challenging because relevant evidence may span multiple entities and their relationshi...