Incorporating Q&A Nuggets into Retrieval-Augmented Generation

Laura Dietz, Bryan Li, Gabrielle K. Liu, Jia-Huei Ju, Eugene Yang, Dawn J. Lawrie, William Gantt Walden, James Mayfield

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.

External IDs:dblp:journals/corr/abs-2601-13222