mlsanityData to 7 Oct 2026

Why Can Large Language Models Generate Correct Chain-of-Thoughts?

arXiv 2310.13571 ↗First posted 20 Oct 2023cs.CLcited by 16

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

Abstract (arXiv)

This paper delves into the capabilities of large language models (LLMs), specifically focusing on advancing the theoretical comprehension of chain-of-thought prompting. We investigate how LLMs can be effectively induced to generate a coherent chain of thoughts. To achieve this, we introduce a two-level hierarchical graphical model tailored for natural language generation. Within this framework, we establish a compelling geometrical convergence rate that gauges the likelihood of an LLM-generated chain of thoughts compared to those originating from the true language. Our findings provide a theoretical justification for the ability of LLMs to produce the correct sequence of thoughts (potentially) explaining performance gains in tasks demanding reasoning skills.

Key facts. Cited by 16 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 73 references that are in the map. First posted on arXiv 20 Oct 2023.

Builds on

38 of 73 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution28 Sep
  2. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Models18 Aug
  3. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks22 Nov

Other references · 35

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  4. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  5. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  6. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  7. 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,332
  8. 2023Large Language Models as Optimizerscited by 830
  9. 2023Capabilities of GPT-4 on Medical Challenge Problemscited by 630
  10. 2023Towards Expert-Level Medical Question Answering with Large Language Modelscited by 382
  11. 2023FreshLLMs: Refreshing Large Language Models with Search Engine Augmentationcited by 308
  12. 2023CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-Xcited by 294
23 more
  1. 2023Sentiment Analysis in the Era of Large Language Models: A Reality Checkcited by 262
  2. 2022Leveraging Large Language Models for Multiple Choice Question Answeringcited by 199
  3. 2023OpenAGI: When LLM Meets Domain Expertscited by 196
  4. 2023EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizerscited by 189
  5. 2023EvoPrompting: Language Models for Code-Level Neural Architecture Searchcited by 129
  6. 2023DeID-GPT: Zero-shot Medical Text De-Identification by GPT-4cited by 128
  7. 2023Emergent autonomous scientific research capabilities of large language modelscited by 127
  8. 2023The Learnability of In-Context Learningcited by 126
  9. 2021Self-supervised Learning is More Robust to Dataset Imbalancecited by 122
  10. 2023Are Emergent Abilities in Large Language Models just In-Context Learning?cited by 109
  11. 2022Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Modelscited by 108
  12. 2023Is ChatGPT a Good Sentiment Analyzer? A Preliminary Studycited by 96
  13. 2023A Theory of Emergent In-Context Learning as Implicit Structure Inductioncited by 86
  14. 2023Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Familycited by 71
  15. 2022Code4Struct: Code Generation for Few-Shot Event Structure Predictioncited by 70
  16. 2023PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedbackcited by 69
  17. 2023HAGRID: A Human-LLM Collaborative Dataset for Generative Information-Seeking with Attributioncited by 55
  18. 2023Learning to Generate Better Than Your LLMcited by 49
  19. 2023A Latent Space Theory for Emergent Abilities in Large Language Modelscited by 42
  20. 2023LLM as A Robotic Brain: Unifying Egocentric Memory and Controlcited by 32
  21. 2023Detecting LLM-Generated Text in Computing Education: A Comparative Study for ChatGPT Casescited by 32
  22. 2023Numeracy from Literacy: Data Science as an Emergent Skill from Large Language Modelscited by 8
  23. 2023Enhancing In-Context Learning with Answer Feedback for Multi-Span Question Answeringcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 7; 2025: 4; 2026: 4.

16 papers.

Sort:

By area:

  1. 2024Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Modelscited by 104
  2. 2023The Expressive Power of Low-Rank Adaptationcited by 100
  3. 2024Demystifying Chains, Trees, and Graphs of Thoughtscited by 63
  4. 2025A Survey on Large Language Models for Mathematical Reasoningcited by 52
  5. 2025Transformers Learn to Implement Multi-step Gradient Descent with Chain of Thoughtcited by 32
  6. 2024ROS-LLM: A ROS framework for embodied AI with task feedback and structured reasoningcited by 27
  7. 2024Unveiling the Statistical Foundations of Chain-of-Thought Prompting Methodscited by 27
  8. 2025A Tutorial on LLM Reasoning: Relevant Methods behind ChatGPT o1cited by 24
  9. 2024Kolb-Based Experiential Learning for Generalist Agents with Human-Level Kaggle Data Science Performancecited by 22
  10. 2024A Theoretical Understanding of Chain-of-Thought: Coherent Reasoning and Error-Aware Demonstrationcited by 13
  11. 2024Make LLMs better zero-shot reasoners: Structure-orientated autonomous reasoningcited by 6
  12. 2025Self-Verifying Reflection Helps Transformers with CoT Reasoningcited by 4
4 more
  1. 2026Decoding as Optimisation on the Probability Simplex: From Top-K to Top-P (Nucleus) to Best-of-K Samplerscited by 2
  2. 2026Opening the Black Box: A Survey on the Mechanisms of Multi-Step Reasoning in Large Language Modelscited by 1
  3. 2026Demonstrations, CoT, and Prompting: A Theoretical Analysis of ICLcited by 0
  4. 2026On the Cost and Benefit of Chain of Thought: A Learning-Theoretic Perspectivecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  2. 2024Chain-of-Thought in Large Language Models: Decoding, Projection, and Activation
  3. 2025On the Thinking-Language Modeling Gap in Large Language Models
  4. 2024General Purpose Verification for Chain of Thought Prompting
  5. 2023Beyond Words: A Mathematical Framework for Interpreting Large Language Models
  6. 2023Boosting Language Models Reasoning with Chain-of-Knowledge Prompting
  7. 2025Beyond Chains of Thought: Benchmarking Latent-Space Reasoning Abilities in Large Language Models
  8. 2026Fragile Thoughts: How Large Language Models Handle Chain-of-Thought Perturbations