mlsanityData to 7 Oct 2026

Incorporating Q&A Nuggets into Retrieval-Augmented Generation

arXiv 2601.13222 ↗First posted 19 Jan 2026cs.IR cs.AIcited by 2

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 24 of its 35 references that are in the map. First posted on arXiv 19 Jan 2026.

Builds on

24 of 35 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct
  2. 2021End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering9 Jun

Other references · 22

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  3. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  4. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  5. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,175
  6. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 508
  7. 2023What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuningcited by 354
  8. 2024xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Tokencited by 123
  9. 2024IM-RAG: Multi-Round Retrieval-Augmented Generation Through Learning Inner Monologuescited by 40
  10. 2024Initial Nugget Evaluation Results for the TREC 2024 RAG Track with the AutoNuggetizer Frameworkcited by 28
  11. 2025The Great Nugget Recall: Automating Fact Extraction and RAG Evaluation with Large Language Modelscited by 24
  12. 2024On the Evaluation of Machine-Generated Reportscited by 23
10 more
  1. 2024Translate-Distill: Learning Cross-Language Dense Retrieval by Translation and Distillationcited by 22
  2. 2024Researchy Questions: A Dataset of Multi-Perspective, Decompositional Questions for LLM Web Agentscited by 22
  3. 2024A Large-Scale Study of Relevance Assessments with Large Language Models: An Initial Lookcited by 18
  4. 2025GINGER: Grounded Information Nugget-Based Generation of Responsescited by 16
  5. 2025Auto-ARGUE: LLM-Based Report Generation Evaluationcited by 14
  6. 2025Overview of the TREC 2024 NeuCLIR Trackcited by 13
  7. 2024A Workbench for Autograding Retrieve/Generate Systemscited by 9
  8. 2025Milco: Learned Sparse Retrieval Across Languages via a Multilingual Connectorcited by 9
  9. 2025HLTCOE at LiveRAG: GPT-Researcher using ColBERT retrievalcited by 6
  10. 2025HLTCOE at TREC 2024 NeuCLIR Trackcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Beyond Relevance: On the Relationship Between Retrieval and RAG Information Coveragecited by 1
  2. 2026CoinRAG: Contextualized Information Nugget KV Cache Reuse for Long-Context RAGcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026NuggetIndex: Governed Atomic Retrieval for Maintainable RAG
  2. 2026DoGMaTiQ: Automated Generation of Question-and-Answer Nuggets for Report Evaluation
  3. 2026DS@GT ARC at LongEval: Citation Integrity and Factual Grounding in Scientific QA
  4. 2024On the Capacity of Citation Generation by Large Language Models
  5. 2025VeriCite: Towards Reliable Citations in Retrieval-Augmented Generation via Rigorous Verification
  6. 2025A Systematic Literature Review of Retrieval-Augmented Generation: Techniques, Metrics, and Challenges
  7. 2025TrustRAG: An Information Assistant with Retrieval Augmented Generation
  8. 2024Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation