Incorporating Q&A Nuggets into Retrieval-Augmented Generation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Dietz, Laura, Li, Bryan, Liu, Gabrielle, Ju, Jia-Huei, Yang, Eugene, Lawrie, Dawn, Walden, William, Mayfield, James
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914426259505152
author Dietz, Laura
Li, Bryan
Liu, Gabrielle
Ju, Jia-Huei
Yang, Eugene
Lawrie, Dawn
Walden, William
Mayfield, James
author_facet Dietz, Laura
Li, Bryan
Liu, Gabrielle
Ju, Jia-Huei
Yang, Eugene
Lawrie, Dawn
Walden, William
Mayfield, James
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_13222
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Incorporating Q&A Nuggets into Retrieval-Augmented Generation
Dietz, Laura
Li, Bryan
Liu, Gabrielle
Ju, Jia-Huei
Yang, Eugene
Lawrie, Dawn
Walden, William
Mayfield, James
Information Retrieval
Artificial Intelligence
H.3
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.
title Incorporating Q&A Nuggets into Retrieval-Augmented Generation
topic Information Retrieval
Artificial Intelligence
H.3
url https://arxiv.org/abs/2601.13222