[2601.13222] Incorporating Q&A Nuggets into Retrieval-Augmented Generation

Computer Science > Information Retrieval arXiv:2601.13222 (cs) [Submitted on 19 Jan 2026 (v1), last revised 27 Mar 2026 (this version, v2)] Title:Incorporating Q&A Nuggets into Retrieval-Augmented Generation Authors:Laura Dietz, Bryan Li, Gabrielle Liu, Jia-Huei Ju, Eugene Yang, Dawn Lawrie, William Walden, James Mayfield View a PDF of the paper titled Incorporating Q&A Nuggets into Retrieval-Augmented Generation, by Laura Dietz and 7 other authors View PDF HTML (experimental) Abstract:RAGE systems integrate ideas from automatic evaluation (E) into Retrieval-augmented Generation (RAG). As one such example, we present Crucible, a Nugget-Augmented Generation System that preserves explicit citation provenance by constructing a bank of Q&A nuggets from retrieved documents and uses them to guide extraction, selection, and report generation. Reasoning on nuggets avoids repeated information through clear and interpretable Q&A semantics - instead of opaque cluster abstractions - while maintaining citation provenance throughout the entire generation process. Evaluated on the TREC NeuCLIR 2024 collection, our Crucible system substantially outperforms Ginger, a recent nugget-based RAG system, in nugget recall, density, and citation grounding. Comments: Subjects: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI) ACM classes: H.3 Cite as: arXiv:2601.13222 [cs.IR]   (or arXiv:2601.13222v2 [cs.IR] for this version)   https://doi.org/10.48550/arXiv.2601.13222 Focus to learn m...