mlsanityData to 14 Oct 2026

RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generation

arXiv 2502.10996 ↗First posted 16 Feb 2025cs.CLcited by 16

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) have achieved impressive performance on knowledge-intensive tasks, yet they often struggle with multi-step reasoning due to the unstructured nature of retrieved context. While retrieval-augmented generation (RAG) methods provide external information, the lack of explicit organization among retrieved passages limits their effectiveness, leading to brittle reasoning pathways. Recent interpretability studies highlighting the importance of structured intermediate reasoning further align with this perspective. We propose Retrieval-And-Structuring (RAS), a framework that dynamically constructs question-specific knowledge graphs through iterative retrieval and structured knowledge building. RAS interleaves targeted retrieval planning with incremental graph construction, enabling models to assemble and reason over evolving knowledge structures tailored to each query. On seven knowledge-intensive benchmarks, RAS consistently outperforms strong baselines, achieving up to 8.7% and 7.0% gains with proprietary and open-source LLMs, respectively. Our results demonstrate that dynamic, question-specific knowledge structuring offers a robust path to improving reasoning accuracy and robustness in language model generation.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 65 of its 82 references that are in the map. First posted on arXiv 16 Feb 2025.

Builds on

65 of 82 references.

References · 65

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2024The Llama 3 Herd of Modelscited by 14,715
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  5. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  6. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  7. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  8. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  9. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,886
  10. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  11. 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
  12. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
38 more
  1. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  2. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  3. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  4. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  5. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  6. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  7. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,202
  8. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  9. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  10. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  11. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  12. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 900
  13. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 698
  14. 2021P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Taskscited by 689
  15. 2020Knowledge Graphscited by 621
  16. 2023Enabling Large Language Models to Generate Text with Citationscited by 595
  17. 2019ELI5: Long Form Question Answeringcited by 575
  18. 2023Active Retrieval Augmented Generationcited by 516
  19. 2020Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classificationcited by 506
  20. 2021MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontierscited by 470
  21. 2023Ragas: Automated Evaluation of Retrieval Augmented Generationcited by 418
  22. 2021QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answeringcited by 388
  23. 2024The Faiss librarycited by 376
  24. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 346
  25. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 328
  26. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 318
  27. 2019ERNIE: Enhanced Representation through Knowledge Integrationcited by 302
  28. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 281
  29. 2024Nomic Embed: Training a Reproducible Long Context Text Embeddercited by 265
  30. 2023RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentationcited by 256
  31. 2022ASQA: Factoid Questions Meet Long-Form Answerscited by 234
  32. 2024G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answeringcited by 223
  33. 2022Deep Bidirectional Language-Knowledge Graph Pretrainingcited by 156
  34. 2023Deductive Verification of Chain-of-Thought Reasoningcited by 124
  35. 2020A Survey of Knowledge-Enhanced Text Generationcited by 120
  36. 2024Let Your Graph Do the Talking: Encoding Structured Data for LLMscited by 118
  37. 2021Measure and Improve Robustness in NLP Models: A Surveycited by 107
  38. 2019A Discrete Hard EM Approach for Weakly Supervised Question Answeringcited by 78

50 most cited of 65 All 65 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 8; 2026: 8.

16 papers.

Sort:

By area:

  1. 2025A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challengescited by 62
  2. 2025Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skillscited by 22
  3. 2025TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Frameworkcited by 7
  4. 2026EHR-RAG: Bridging Long-Horizon Structured Electronic Health Records and Large Language Models via Enhanced Retrieval-Augmented Generationcited by 6
  5. 2026RAG or Learning? Understanding the Limits of LLM Adaptation under Continuous Knowledge Drift in the Real Worldcited by 4
  6. 2025Enhancing LLMs' Reasoning-Intensive Multimedia Search Capabilities through Fine-Tuning and Reinforcement Learningcited by 3
  7. 2026Only Ask What You Don't Know: Grounded Delta Planning for Efficient Multi-step RAGcited by 3
  8. 2025Structure-Augmented Reasoning Generationcited by 2
  9. 2025Zero-Shot Open-Schema Entity Structure Discoverycited by 1
  10. 2025Learning to Debug: LLM-Organized Knowledge Trees for Solving RTL Assertion Failurescited by 1
  11. 2026Disco-RAG: Discourse-Aware Retrieval-Augmented Generationcited by 1
  12. 2025jXBW: A Compressed Index Enabling Structure-Aware JSONL Retrieval for Structured RAGcited by 0
4 more
  1. 2026Condition-Gated Reasoning for Context-Dependent Biomedical Question Answeringcited by 0
  2. 2026MedJudgeRAG: Option-Wise Evidence Judgment with Dynamic Knowledge Graphs for Medical MCQAcited by 0
  3. 2026Select-And-Extract: A Lightweight Plugin for Retrieval-Augmented Generationcited by 0
  4. 2026Event-Centric Memory with Query-Aware Graph Augmentation for Long-Term Conversational Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025A Survey on Retrieval And Structuring Augmented Generation with Large Language Models
  2. 2025FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs
  3. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models
  4. 2024Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation
  5. 2024StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization
  6. 2023Retrieval-Generation Synergy Augmented Large Language Models
  7. 2023DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text
  8. 2024Mindful-RAG: A Study of Points of Failure in Retrieval Augmented Generation