mlsanityData to 7 Oct 2026

Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive Tasks

arXiv 2304.14732 ↗First posted 28 Apr 2023cs.CLcited by 73

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Making the content generated by Large Language Model (LLM), accurate, credible and traceable is crucial, especially in complex knowledge-intensive tasks that require multi-step reasoning and each step needs knowledge to solve. Retrieval-augmented generation is good potential to solve this problem. However, where and how to introduce Information Retrieval (IR) to LLM is a big challenge. Previous work has the problems that wrong knowledge retrieved by IR misleads the LLM and interaction between IR and LLM breaks the reasoning chain of LLM. This paper proposes a novel framework named Search-in-the-Chain (SearChain) for the interaction between LLM and IR to solve the challenges. First, LLM generates the reasoning chain named Chain-of-Query (CoQ) where each node consists of an IR-oriented query-answer pair. Second, IR verifies the answer of each node of CoQ. It corrects the answer that is not consistent with the retrieved information when IR gives high confidence, which improves the credibility. Third, LLM can indicate its missing knowledge in CoQ and rely on IR to provide this knowledge to LLM. These operations improve the accuracy in terms of reasoning and knowledge. Finally, SearChain generates the reasoning process and marks references to supporting documents for each reasoning step, which improves traceability. Interaction with IR in SearChain forms a novel reasoning path based on a tree, which enables LLM to dynamically modify the direction of reasoning. Experiments show that SearChain outperforms state-of-the-art baselines on complex knowledge-intensive tasks including multi-hop Q&A, slot filling, fact checking, and long-form Q&A.

Key facts. Cited by 73 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 22 of its 46 references that are in the map. First posted on arXiv 28 Apr 2023.

Builds on

22 of 46 references.

References · 22

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  4. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  5. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  6. 2023A Survey of Large Language Modelscited by 2,537
  7. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  8. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  9. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,362
  10. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  11. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  12. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
10 more
  1. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,054
  2. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 893
  3. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 571
  4. 2019ELI5: Long Form Question Answeringcited by 567
  5. 2022Large Language Models Struggle to Learn Long-Tail Knowledgecited by 452
  6. 2022Complexity-Based Prompting for Multi-Step Reasoningcited by 387
  7. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 316
  8. 2020Knowledge-Aware Language Model Pretrainingcited by 52
  9. 2023WebBrain: Learning to Generate Factually Correct Articles for Queries by Grounding on Large Web Corpuscited by 29
  10. 2021Narrative Question Answering with Cutting-Edge Open-Domain QA Techniques: A Comprehensive Studycited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 24; 2025: 37; 2026: 12.

73 papers.

Sort:

By area:

  1. 2024Tool Learning with Large Language Models: A Surveycited by 221
  2. 2024InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationalescited by 100
  3. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Modelscited by 85
  4. 2024MindSearch: Mimicking Human Minds Elicits Deep AI Searchercited by 65
  5. 2025Deep Research: A Survey of Autonomous Research Agentscited by 63
  6. 2025A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challengescited by 58
  7. 2024Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMscited by 48
  8. 2025Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learningcited by 39
  9. 2024RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinementcited by 38
  10. 2025Large Language Models for Planning: A Comprehensive and Systematic Surveycited by 38
  11. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generationcited by 34
  12. 2025Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Homecited by 33
38 more
  1. 2025Topic-FlipRAG: Topic-Orientated Adversarial Opinion Manipulation Attacks to Retrieval-Augmented Generation Modelscited by 32
  2. 2024Improving Retrieval Augmented Language Model with Self-Reasoningcited by 28
  3. 2024RAGAR, Your Falsehood Radar: RAG-Augmented Reasoning for Political Fact-Checking using Multimodal Large Language Modelscited by 27
  4. 2026SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinementcited by 24
  5. 2024Claim Verification in the Age of Large Language Models: A Surveycited by 23
  6. 2025A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applicationscited by 21
  7. 2024Everything is Editable: Extend Knowledge Editing to Unstructured Data in Large Language Modelscited by 18
  8. 2024Cross-Modal Safety Mechanism Transfer in Large Vision-Language Modelscited by 18
  9. 2024RichRAG: Crafting Rich Responses for Multi-faceted Queries in Retrieval-Augmented Generationcited by 16
  10. 2024ALiiCE: Evaluating Positional Fine-grained Citation Generationcited by 15
  11. 2024Hierarchical Retrieval-Augmented Generation Model with Rethink for Multi-hop Question Answeringcited by 14
  12. 2025Following the Autoregressive Nature of LLM Embeddings via Compression and Alignmentcited by 14
  13. 2025Question Decomposition for Retrieval-Augmented Generationcited by 11
  14. 2025RLKD: Distilling LLMs' Reasoning via Reinforcement Learningcited by 10
  15. 2024Length-Induced Embedding Collapse in PLM-based Modelscited by 9
  16. 2025Mining Intrinsic Rewards from LLM Hidden States for Efficient Best-of-N Samplingcited by 9
  17. 2025QAgent: A modular Search Agent with Interactive Query Understandingcited by 8
  18. 2026CL-bench Life: Can Language Models Learn from Real-Life Context?cited by 8
  19. 2024Leveraging the Domain Adaptation of Retrieval Augmented Generation Models for Question Answering and Reducing Hallucinationcited by 7
  20. 2025MDEval: Evaluating and Enhancing Markdown Awareness in Large Language Modelscited by 7
  21. 2026GRACE: Reinforcement Learning for Grounded Response and Abstention under Contextual Evidencecited by 6
  22. 2024Exploring the Escalation of Source Bias in User, Data, and Recommender System Feedback Loopcited by 5
  23. 2024Citekit: A Modular Toolkit for Large Language Model Citation Generationcited by 5
  24. 2025Learning to Rank Chain-of-Thought: Using a Small Modelcited by 5
  25. 2025POQD: Performance-Oriented Query Decomposer for Multi-vector retrievalcited by 5
  26. 2025Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimizationcited by 5
  27. 2025Large Language Model Sourcing: A Surveycited by 5
  28. 2026PruneRAG: Confidence-Guided Query Decomposition Trees for Efficient Retrieval-Augmented Generationcited by 5
  29. 2024LINKAGE: Listwise Ranking among Varied-Quality References for Non-Factoid QA Evaluation via LLMscited by 4
  30. 2024ConTReGen: Context-driven Tree-structured Retrieval for Open-domain Long-form Text Generationcited by 4
  31. 2025Transparentize the Internal and External Knowledge Utilization in LLMs with Trustworthy Citationcited by 4
  32. 2025ReSCORE: Label-free Iterative Retriever Training for Multi-hop Question Answering with Relevance-Consistency Supervisioncited by 4
  33. 2026Glance-or-Gaze: Incentivizing LMMs to Adaptively Focus Search via Reinforcement Learningcited by 4
  34. 2024Zero-Shot Multi-Hop Question Answering via Monte-Carlo Tree Search with Large Language Modelscited by 3
  35. 2024Generating a Low-code Complete Workflow via Task Decomposition and RAGcited by 3
  36. 2025AttackSeqBench: Benchmarking the Capabilities of LLMs for Attack Sequences Understandingcited by 3
  37. 2025Test-time Corpus Feedback: From Retrieval to RAGcited by 3
  38. 2026OptiSet: Unified Optimizing Set Selection and Ranking for Retrieval-Augmented Generationcited by 3

50 most cited of 73 All 73 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023RETA-LLM: A Retrieval-Augmented Large Language Model Toolkit
  2. 2024Retrieving, Rethinking and Revising: The Chain-of-Verification Can Improve Retrieval Augmented Generation
  3. 2023DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text
  4. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions
  5. 2025LLM-guided Hierarchical Search for End-to-end Reasoning Intensive Retrieval
  6. 2025FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs
  7. 2026Over-Searching in Search-Augmented Large Language Models
  8. 2025Improving Context Fidelity via Native Retrieval-Augmented Reasoning