mlsanityData to 14 Oct 2026

PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation

arXiv 2501.11551 ↗First posted 20 Jan 2025cs.CLcited by 18

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

Abstract (arXiv)

Despite notable advancements in Retrieval-Augmented Generation (RAG) systems that expand large language model (LLM) capabilities through external retrieval, these systems often struggle to meet the complex and diverse needs of real-world industrial applications. The reliance on retrieval alone proves insufficient for extracting deep, domain-specific knowledge performing in logical reasoning from specialized corpora. To address this, we introduce sPecIalized KnowledgE and Rationale Augmentation Generation (PIKE-RAG), focusing on extracting, understanding, and applying specialized knowledge, while constructing coherent rationale to incrementally steer LLMs toward accurate responses. Recognizing the diverse challenges of industrial tasks, we introduce a new paradigm that classifies tasks based on their complexity in knowledge extraction and application, allowing for a systematic evaluation of RAG systems' problem-solving capabilities. This strategic approach offers a roadmap for the phased development and enhancement of RAG systems, tailored to meet the evolving demands of industrial applications. Furthermore, we propose knowledge atomizing and knowledge-aware task decomposition to effectively extract multifaceted knowledge from the data chunks and iteratively construct the rationale based on original query and the accumulated knowledge, respectively, showcasing exceptional performance across various benchmarks.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 37 of its 54 references that are in the map. First posted on arXiv 20 Jan 2025.

Builds on

37 of 54 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Modular RAG: Transforming RAG Systems into LEGO-like Reconfigurable Frameworks26 Jul
  2. 2024Retrieval-Augmented Generation for AI-Generated Content: A Survey29 Feb
  3. 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec

Other references · 34

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  5. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  6. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  7. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  8. 2024Qwen2 Technical Reportcited by 2,120
  9. 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,356
  10. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  11. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  12. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
22 more
  1. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  2. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 916
  3. 2023Large Language Modelscited by 780
  4. 2023In-Context Retrieval-Augmented Language Modelscited by 702
  5. 2020Fact or Fiction: Verifying Scientific Claimscited by 554
  6. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 517
  7. 2023LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compressioncited by 453
  8. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 346
  9. 2024Hallucination is Inevitable: An Innate Limitation of Large Language Modelscited by 332
  10. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 318
  11. 2023Query Rewriting for Retrieval-Augmented Large Language Modelscited by 213
  12. 2023Take a Step Back: Evoking Reasoning via Abstraction in Large Language Modelscited by 159
  13. 2023Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Surveycited by 135
  14. 2023LawBench: Benchmarking Legal Knowledge of Large Language Modelscited by 117
  15. 2023Dense X Retrieval: What Retrieval Granularity Should We Use?cited by 88
  16. 2019Hierarchical Graph Network for Multi-hop Question Answeringcited by 83
  17. 2020WikiAsp: A Dataset for Multi-domain Aspect-based Summarizationcited by 56
  18. 2023KnowledGPT: Enhancing Large Language Models with Retrieval and Storage Access on Knowledge Basescited by 52
  19. 2023End-to-End Beam Retrieval for Multi-Hop Question Answeringcited by 35
  20. 2023ChatGPT: Applications, Opportunities, and Threatscited by 28
  21. 2024Mix-of-Granularity: Optimize the Chunking Granularity for Retrieval-Augmented Generationcited by 23
  22. 2023Leveraging Structured Information for Explainable Multi-hop Question Answering and Reasoningcited by 22

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 13; 2026: 5.

18 papers.

Sort:

By area:

  1. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Modelscited by 88
  2. 2025When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented Generationcited by 48
  3. 2025A Survey of Multimodal Retrieval-Augmented Generationcited by 37
  4. 2025Large Language Models Meet Knowledge Graphs for Question Answering: Synthesis and Opportunitiescited by 31
  5. 2025ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generationcited by 28
  6. 2025Synergizing RAG and Reasoning: A Systematic Reviewcited by 27
  7. 2025SeCon-RAG: A Two-Stage Semantic Filtering and Conflict-Free Framework for Trustworthy RAGcited by 13
  8. 2025EviNote-RAG: Enhancing RAG Models via Answer-Supportive Evidence Notescited by 8
  9. 2025RAKG:Document-level Retrieval Augmented Knowledge Graph Constructioncited by 4
  10. 2025Towards Transparent RAG: Fostering Evidence Traceability in LLM Generation via Reinforcement Learningcited by 4
  11. 2026Agents-K1: Towards Agent-native Knowledge Orchestrationcited by 3
  12. 2025SKA-Bench: A Fine-Grained Benchmark for Evaluating Structured Knowledge Understanding of LLMscited by 1
6 more
  1. 2025In-Context Compositional Q-Learning for Offline Reinforcement Learningcited by 1
  2. 2026When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answeringcited by 1
  3. 2026Citation-Closure Retrieval and Per-Rule Attribution for Real-World Regulatory Compliance Question Answeringcited by 1
  4. 2025GOSU: Retrieval-Augmented Generation with Global-Level Optimized Semantic Unit-Centric Frameworkcited by 0
  5. 2026C-GRASP: Clinically-Grounded Reasoning for Affective Signal Processingcited by 0
  6. 2026RAGA: Reading-And-Graph-building-Agent for Autonomous Knowledge Graph Construction and Retrieval-Augmented Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025RAG+: Enhancing Retrieval-Augmented Generation with Application-Aware Reasoning
  2. 2025Dynamic and Parametric Retrieval-Augmented Generation
  3. 2024A Hybrid RAG System with Comprehensive Enhancement on Complex Reasoning
  4. 2025Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs
  5. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generation
  6. 2024StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization
  7. 2024Retrieval-Augmented Generation for Natural Language Processing: A Survey
  8. 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning