mlsanityData to 7 Oct 2026

Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answering

arXiv 2308.13259 ↗First posted 25 Aug 2023cs.CL cs.AIcited by 97

On the map: LLM reasoning → Prompting and chain-of-thought reasoning

Abstract (arXiv)

Equipped with Chain-of-Thought (CoT), Large language models (LLMs) have shown impressive reasoning ability in various downstream tasks. Even so, suffering from hallucinations and the inability to access external knowledge, LLMs often come with incorrect or unfaithful intermediate reasoning steps, especially in the context of answering knowledge-intensive tasks such as KBQA. To alleviate this issue, we propose a framework called Knowledge-Driven Chain-of-Thought (KD-CoT) to verify and modify reasoning traces in CoT via interaction with external knowledge, and thus overcome the hallucinations and error propagation. Concretely, we formulate the CoT rationale process of LLMs into a structured multi-round QA format. In each round, LLMs interact with a QA system that retrieves external knowledge and produce faithful reasoning traces based on retrieved precise answers. The structured CoT reasoning of LLMs is facilitated by our developed KBQA CoT collection, which serves as in-context learning demonstrations and can also be utilized as feedback augmentation to train a robust retriever. Extensive experiments on WebQSP and ComplexWebQuestion datasets demonstrate the effectiveness of proposed KD-CoT in task-solving reasoning generation, which outperforms the vanilla CoT ICL with an absolute success rate of 8.0% and 5.1%. Furthermore, our proposed feedback-augmented retriever outperforms the state-of-the-art baselines for retrieving knowledge, achieving significant improvement in Hit and recall performance. Our code and data are released on https://github.com/AdelWang/KD-CoT/tree/main.

Key facts. Cited by 97 papers in the map (data through 7 Oct 2026). Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. Builds on 38 of its 40 references that are in the map. First posted on arXiv 25 Aug 2023.

Builds on

38 of 40 references.

Closest ancestors · 6

Same direction, newest first

  1. 2023Boosting Language Models Reasoning with Chain-of-Knowledge Prompting10 Jun
  2. 2023Tab-CoT: Zero-shot Tabular Chain of Thought28 May
  3. 2023CoTEVer: Chain of Thought Prompting Annotation Toolkit for Explanation Verification7 Mar
  4. 2023Faithful Chain-of-Thought Reasoning31 Jan
  5. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Models21 May
  6. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Models21 Mar

Other references · 32

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  6. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  7. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  8. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  9. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  10. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  11. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  12. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
20 more
  1. 2022Emergent Abilities of Large Language Modelscited by 2,483
  2. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  3. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  4. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,054
  5. 2021GLM: General Language Model Pretraining with Autoregressive Blank Infillingcited by 1,026
  6. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 888
  7. 2018The Web as a Knowledge-base for Answering Complex Questionscited by 409
  8. 2023Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedbackcited by 351
  9. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 331
  10. 2022Rethinking with Retrieval: Faithful Large Language Model Inferencecited by 145
  11. 2022Faithful Reasoning Using Large Language Modelscited by 130
  12. 2019Multi-hop Reading Comprehension through Question Decomposition and Rescoringcited by 119
  13. 2021Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signalscited by 100
  14. 2023WebGLM: Towards An Efficient Web-Enhanced Question Answering System with Human Preferencescited by 100
  15. 2022DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Basescited by 83
  16. 2021KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answeringcited by 66
  17. 2020Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Modelscited by 65
  18. 2020UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answeringcited by 61
  19. 2020SPARQA: Skeleton-based Semantic Parsing for Complex Questions over Knowledge Basescited by 47
  20. 2023Expand, Rerank, and Retrieve: Query Reranking for Open-Domain Question Answeringcited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 39; 2025: 42; 2026: 10.

97 papers.

Sort:

By area:

  1. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 352
  2. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 326
  3. 2024Graph Retrieval-Augmented Generation: A Surveycited by 320
  4. 2023Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Futurecited by 184
  5. 2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Modelscited by 180
  6. 2024GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoningcited by 128
  7. 2024The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Modelscited by 87
  8. 2024Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generationcited by 78
  9. 2024Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphscited by 77
  10. 2024PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generationcited by 77
  11. 2025A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challengescited by 58
  12. 2025Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendationcited by 56
38 more
  1. 2024Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMscited by 48
  2. 2024Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Modelscited by 47
  3. 2025In-depth Analysis of Graph-based RAG in a Unified Frameworkcited by 45
  4. 2024FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answeringcited by 38
  5. 2024Causal Prompting: Debiasing Large Language Model Prompting based on Front-Door Adjustmentcited by 29
  6. 2024How Interpretable are Reasoning Explanations from Prompting Large Language Models?cited by 27
  7. 2025ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generationcited by 27
  8. 2023HyKGE: A Hypothesis Knowledge Graph Enhanced Framework for Accurate and Reliable Medical LLMs Responsescited by 25
  9. 2024Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentationcited by 24
  10. 2025A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applicationscited by 21
  11. 2024KnowPO: Knowledge-aware Preference Optimization for Controllable Knowledge Selection in Retrieval-Augmented Language Modelscited by 20
  12. 2024Decoding on Graphs: Faithful and Sound Reasoning on Knowledge Graphs through Generation of Well-Formed Chainscited by 20
  13. 2024Dual Reasoning: A GNN-LLM Collaborative Framework for Knowledge Graph Question Answeringcited by 19
  14. 2025Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Surveycited by 18
  15. 2024LLMs Know What They Need: Leveraging a Missing Information Guided Framework to Empower Retrieval-Augmented Generationcited by 17
  16. 2024Enhancing Complex Question Answering over Knowledge Graphs through Evidence Pattern Retrievalcited by 16
  17. 2025Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question Answeringcited by 15
  18. 2024EffiQA: Efficient Question-Answering with Strategic Multi-Model Collaboration on Knowledge Graphscited by 14
  19. 2024Distilling Reasoning Ability from Large Language Models with Adaptive Thinkingcited by 13
  20. 2024EWEK-QA: Enhanced Web and Efficient Knowledge Graph Retrieval for Citation-based Question Answering Systemscited by 13
  21. 2024OCEAN: Offline Chain-of-thought Evaluation and Alignment in Large Language Modelscited by 12
  22. 2024KnowTuning: Knowledge-aware Fine-tuning for Large Language Modelscited by 11
  23. 2024A Picture Is Worth a Graph: A Blueprint Debate Paradigm for Multimodal Reasoningcited by 11
  24. 2025Diagnosing and Addressing Pitfalls in KG-RAG Datasets: Toward More Reliable Benchmarkingcited by 11
  25. 2025Memory-augmented Query Reconstruction for LLM-based Knowledge Graph Reasoningcited by 10
  26. 2025BYOKG-RAG: Multi-Strategy Graph Retrieval for Knowledge Graph Question Answeringcited by 10
  27. 2025Reliable Reasoning Path: Distilling Effective Guidance for LLM Reasoning with Knowledge Graphscited by 9
  28. 2023Towards A Unified View of Answer Calibration for Multi-Step Reasoningcited by 8
  29. 2024Enhancing Large Language Models with Pseudo- and Multisource- Knowledge Graphs for Open-ended Question Answeringcited by 8
  30. 2024UniRAG: Universal Retrieval Augmentation for Large Vision Language Modelscited by 8
  31. 2025FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphscited by 8
  32. 2025CoT-RAG: Integrating Chain of Thought and Retrieval-Augmented Generation to Enhance Reasoning in Large Language Modelscited by 8
  33. 2024An Empirical Categorization of Prompting Techniques for Large Language Models: A Practitioner's Guidecited by 7
  34. 2024Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Modelscited by 7
  35. 2024LEGO-GraphRAG: Modularizing Graph-based Retrieval-Augmented Generation for Design Space Explorationcited by 7
  36. 2024KARPA: A Training-free Method of Adapting Knowledge Graph as References for Large Language Model's Reasoning Path Aggregationcited by 7
  37. 2025EPERM: An Evidence Path Enhanced Reasoning Model for Knowledge Graph Question and Answeringcited by 7
  38. 2025Reason-Align-Respond: Aligning LLM Reasoning with Knowledge Graphs for KGQAcited by 7

50 most cited of 97 All 97 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Sci-CoT: Leveraging Large Language Models for Enhanced Knowledge Distillation in Small Models for Scientific QA
  2. 2024Direct Evaluation of Chain-of-Thought in Multi-hop Reasoning with Knowledge Graphs
  3. 2024KAM-CoT: Knowledge Augmented Multimodal Chain-of-Thoughts Reasoning
  4. 2024Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs
  5. 2024Understanding Chain-of-Thought in LLMs through Information Theory
  6. 2025Effectiveness of Chain-of-Thought in Distilling Reasoning Capability from Large Language Models
  7. 2024On the Hardness of Faithful Chain-of-Thought Reasoning in Large Language Models
  8. 2025Can Reasoning Path still be Effective as Input? Bridging Post-Reasoning to Chain-of-Thought Compression