Related papers: Incorporating Q&A Nuggets into Retrieval-Augmented Generation

Incorporating Q&A Nuggets into Retrieval-Augmented Generation

URL: http://arxiv.org/abs/2601.13222v1
Date: Mon, 19 Jan 2026 16:57:33 GMT
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,
Abstract summary: Crucible is a Nugget-Augmented Generation System that preserves explicit citation provenance by constructing a bank of Q&A nuggets from retrieved documents.<n> Reasoning on nuggets avoids repeated information through clear and interpretable Q&A semantics.<n>Our system substantially outperforms Ginger, a recent nugget-based RAG system, in nugget recall, density, and citation grounding.
Score: 23.32167679162754
License: http://creativecommons.org/licenses/by-sa/4.0/
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.

Related papers

VeriCite: Towards Reliable Citations in Retrieval-Augmented Generation via Rigorous Verification [107.75781898355562]
We introduce a novel framework, called VeriCite, designed to rigorously validate supporting evidence and enhance answer attribution.<n>We conduct experiments across five open-source LLMs and four datasets, demonstrating that VeriCite can significantly improve citation quality while maintaining the correctness of the answers.
arXiv Detail & Related papers (2025-10-13T13:38:54Z)
The Great Nugget Recall: Automating Fact Extraction and RAG Evaluation with Large Language Models [53.12387628636912]
We propose an automatic evaluation framework that is validated against human annotations.<n>This approach was originally developed for the TREC Question Answering (QA) Track in 2003.<n>We observe strong agreement at the run level between scores derived from fully automatic nugget evaluation and human-based variants.
arXiv Detail & Related papers (2025-04-21T12:55:06Z)
Conversational Gold: Evaluating Personalized Conversational Search System using Gold Nuggets [8.734527090842139]
We introduce a new resource for assessing the retrieval effectiveness and relevance of response generated by RAG systems.<n>Our dataset extends to the TREC iKAT 2024 collection, which includes 17 conversations and 20,575 relevance passage assessments.
arXiv Detail & Related papers (2025-03-12T23:44:10Z)
Unanswerability Evaluation for Retrieval Augmented Generation [74.3022365715597]
UAEval4RAG is a framework designed to evaluate whether RAG systems can handle unanswerable queries effectively.<n>We define a taxonomy with six unanswerable categories, and UAEval4RAG automatically synthesizes diverse and challenging queries.
arXiv Detail & Related papers (2024-12-16T19:11:55Z)
Initial Nugget Evaluation Results for the TREC 2024 RAG Track with the AutoNuggetizer Framework [53.12387628636912]
This report provides an initial look at partial results from the TREC 2024 Retrieval-Augmented Generation (RAG) Track. We have identified RAG evaluation as a barrier to continued progress in information access.
arXiv Detail & Related papers (2024-11-14T17:25:43Z)
Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation [51.8188846284153]
Attributed Text Generation (ATG) is proposed to enhance credibility and verifiability in RAG systems.<n>This paper proposes ReClaim, a fine-grained ATG method that alternates the generation of references and answers step by step.<n>With extensive experiments, we verify the effectiveness of ReClaim in extensive settings, achieving a citation accuracy rate of 90%.
arXiv Detail & Related papers (2024-07-01T20:47:47Z)
RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation [42.82192656794179]
Large Language Models (LLMs) exhibit remarkable capabilities but are prone to generating inaccurate or hallucinatory responses. This limitation stems from their reliance on vast pretraining datasets, making them susceptible to errors in unseen scenarios. Retrieval-Augmented Generation (RAG) addresses this by incorporating external, relevant documents into the response generation process.
arXiv Detail & Related papers (2024-03-31T08:58:54Z)
Distillation Enhanced Generative Retrieval [96.69326099136289]
Generative retrieval is a promising new paradigm in text retrieval that generates identifier strings of relevant passages as the retrieval target. In this work, we identify a viable direction to further enhance generative retrieval via distillation and propose a feasible framework, named DGR. We conduct experiments on four public datasets, and the results indicate that DGR achieves state-of-the-art performance among the generative retrieval methods.
arXiv Detail & Related papers (2024-02-16T15:48:24Z)
Corrective Retrieval Augmented Generation [36.04062963574603]
Retrieval-augmented generation (RAG) relies heavily on relevance of retrieved documents, raising concerns about how the model behaves if retrieval goes wrong. We propose the Corrective Retrieval Augmented Generation (CRAG) to improve the robustness of generation. CRAG is plug-and-play and can be seamlessly coupled with various RAG-based approaches.
arXiv Detail & Related papers (2024-01-29T04:36:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.