mlsanityData to 14 Oct 2026

Structured RAG for Answering Aggregative Questions

arXiv 2511.08505 ↗First posted 11 Nov 2025cs.CL cs.LGcited by 3

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

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) has become the dominant approach for answering questions over large corpora. However, current datasets and methods are highly focused on cases where only a small part of the corpus (usually a few paragraphs) is relevant per query, and fail to capture the rich world of aggregative queries. These require gathering information from a large set of documents and reasoning over them. To address this gap, we propose S-RAG, an approach specifically designed for such queries. At ingestion time, S-RAG constructs a structured representation of the corpus; at inference time, it translates natural-language queries into formal queries over said representation. To validate our approach and promote further research in this area, we introduce two new datasets of aggregative queries: HOTELS and WORLD CUP. Experiments with S-RAG on the newly introduced datasets, as well as on a public benchmark, demonstrate that it substantially outperforms both common RAG systems and long-context LLMs.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 27 of its 28 references that are in the map. First posted on arXiv 11 Nov 2025.

Builds on

27 of 28 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025WixQA: A Multi-Dataset Benchmark for Enterprise Retrieval-Augmented Generation13 May
  2. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct
  3. 2022Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering6 Oct

Other references · 24

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  4. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  5. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  6. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
  7. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  8. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
  9. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  10. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 916
  11. 2023In-Context Retrieval-Augmented Language Modelscited by 702
  12. 2022MTEB: Massive Text Embedding Benchmarkcited by 640
12 more
  1. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 452
  2. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 369
  3. 2023FinanceBench: A New Benchmark for Financial Question Answeringcited by 270
  4. 2024MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queriescited by 257
  5. 2023Retrieval meets Long Context Large Language Modelscited by 115
  6. 2023Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakescited by 111
  7. 2025On the Theoretical Limitations of Embedding-Based Retrievalcited by 104
  8. 2022QAMPARI: An Open-domain Question Answering Benchmark for Questions with Many Answers from Multiple Paragraphscited by 42
  9. 2023QUEST: A Retrieval Dataset of Entity-Seeking Queries with Implicit Set Operationscited by 31
  10. 2018ComQA: A Community-sourced Dataset for Complex Factoid Question Answering with Paraphrase Clusterscited by 29
  11. 2025MoNaCo: More Natural and Complex Questions for Reasoning Across Dozens of Documentscited by 21
  12. 2025FinSage: A Multi-aspect RAG System for Financial Filings Question Answeringcited by 19

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Imagecited by 2
  2. 2026ScalableRAG: High-Quality RAG at Zero Ingestion Costcited by 0
  3. 2026From Retrieval to Customer Context: Evaluating Frontier-Model Systems for Voice-of-Customer Analysiscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026SRAG: RAG with Structured Data Improves Vector Retrieval
  2. 2025A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directions
  3. 2025SAGE: A Framework of Precise Retrieval for RAG
  4. 2026Augmenting Question Answering with A Hybrid RAG Approach
  5. 2024Improving Retrieval for RAG based Question Answering Models on Financial Documents
  6. 2025Question Decomposition for Retrieval-Augmented Generation
  7. 2024A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions
  8. 2024CLAPNQ: Cohesive Long-form Answers from Passages in Natural Questions for RAG systems