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.
@article{arxiv.2601.13222,
title = {Incorporating Q&A Nuggets into Retrieval-Augmented Generation},
author = {Laura Dietz and Bryan Li and Gabrielle Liu and Jia-Huei Ju and Eugene Yang and Dawn Lawrie and William Walden and James Mayfield},
journal= {arXiv preprint arXiv:2601.13222},
year = {2026}
}
Comments
To appear in the Proceedings of ECIR 2026, Lecture Notes in Computer Science, Volume 16484