mlsanityData to 14 Oct 2026

Deciphering the Factors Influencing the Efficacy of Chain-of-Thought: Probability, Memorization, and Noisy Reasoning

arXiv 2407.01687 ↗First posted 1 Jul 2024cs.CL cs.AIcited by 27

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

Abstract (arXiv)

Chain-of-Thought (CoT) prompting has been shown to enhance the multi-step reasoning capabilities of Large Language Models (LLMs). However, debates persist about whether LLMs exhibit abstract generalization or rely on shallow heuristics when given CoT prompts. To understand the factors influencing CoT reasoning we provide a detailed case study of the symbolic reasoning task of decoding shift ciphers, where letters are shifted forward some number of steps in the alphabet. We analyze the pattern of results produced by three LLMs -- GPT-4, Claude 3, and Llama 3.1 -- performing this task using CoT prompting. By focusing on a single relatively simple task, we are able to identify three factors that systematically affect CoT performance: the probability of the task's expected output (probability), what the model has implicitly learned during pre-training (memorization), and the number of intermediate operations involved in reasoning (noisy reasoning). We show that these factors can drastically influence task accuracy across all three LLMs; e.g., when tested with GPT-4, varying the output's probability of occurrence shifts accuracy from 26% to 70%. Overall, we conclude that CoT prompting performance reflects both memorization and a probabilistic version of genuine reasoning. Code and data at this https://github.com/aksh555/deciphering_cot

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. Builds on 10 of its 52 references that are in the map. First posted on arXiv 1 Jul 2024.

Builds on

10 of 52 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Chain of Thoughtlessness? An Analysis of CoT in Planning8 May
  2. 2023Analyzing Chain-of-Thought Prompting in Large Language Models via Gradient-based Feature Attributions25 Jul
  3. 2023Measuring Faithfulness in Chain-of-Thought Reasoning17 Jul
  4. 2022Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango16 Sep

Other references · 6

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2022FOLIO: Natural Language Reasoning with First-Order Logiccited by 235
  3. 2023Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solvecited by 178
  4. 2023What and How does In-Context Learning Learn? Bayesian Model Averaging, Parameterization, and Generalizationcited by 118
  5. 2024Functional Benchmarks for Robust Evaluation of Reasoning Performance, and the Reasoning Gapcited by 79
  6. 2024Pelican Soup Framework: A Theoretical Framework for Language Model Capabilitiescited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 8; 2025: 14; 2026: 5.

27 papers.

Sort:

By area:

  1. 2024On Memorization of Large Language Models in Logical Reasoningcited by 117
  2. 2025Unveiling the Key Factors for Distilling Chain-of-Thought Reasoningcited by 40
  3. 2024Evaluating the Robustness of Analogical Reasoning in Large Language Modelscited by 31
  4. 2024When a language model is optimized for reasoning, does it still show embers of autoregression? An analysis of OpenAI o1cited by 22
  5. 2025Large Language Models and Mathematical Reasoning Failurescited by 22
  6. 2025The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Directioncited by 21
  7. 2025Chain-of-Thought Prompting Obscures Hallucination Cues in Large Language Models: An Empirical Evaluationcited by 21
  8. 2024MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex Proofscited by 12
  9. 2024Beyond Math: Stories as a Testbed for Memorization-Constrained Reasoning in LLMscited by 12
  10. 2025Compositional Generalization from Learned Skills via CoT Training: A Theoretical and Structural Analysis for Reasoningcited by 10
  11. 2025ProRefine: Inference-Time Prompt Refinement with Textual Feedbackcited by 8
  12. 2026Can Textual Reasoning Improve the Performance of MLLMs on Fine-grained Visual Classification?cited by 8
15 more
  1. 2024Chain-of-Thought in Large Language Models: Decoding, Projection, and Activationcited by 6
  2. 2025None of the Others: a General Technique to Distinguish Reasoning from Memorization in Multiple-Choice LLM Evaluation Benchmarkscited by 6
  3. 2024Ask-Before-Detection: Identifying and Mitigating Conformity Bias in LLM-Powered Error Detector for Math Word Problem Solutionscited by 4
  4. 2025CoT-ICL Lab: A Synthetic Framework for Studying Chain-of-Thought Learning from In-Context Demonstrationscited by 4
  5. 2025The Hitchhiker's Guide to Program Analysis, Part II: Deep Thoughts by LLMscited by 4
  6. 2025Identifying and Mitigating the Influence of the Prior Distribution in Large Language Modelscited by 4
  7. 2024Active Prompt Tuning Enables Gpt-40 To Do Efficient Classification Of Microscopy Imagescited by 2
  8. 2025Function Induction and Task Generalization: An Interpretability Study with Off-by-One Additioncited by 2
  9. 2026Task Complexity Matters: An Empirical Study of Reasoning in LLMs for Sentiment Analysiscited by 2
  10. 2025Semantic Deception: When Reasoning Models Can't Compute an Additioncited by 1
  11. 2025On the Thinking-Language Modeling Gap in Large Language Modelscited by 0
  12. 2025Engineering Sentiencecited by 0
  13. 2026Chart-RL: Policy Optimization Reinforcement Learning for Enhanced Visual Reasoning in Chart Question Answering with Vision Language Modelscited by 0
  14. 2026Strategy-Induct: Task-Level Strategy Induction for Instruction Generationcited by 0
  15. 2026Anthropomorphism in the age of Large Language Models: An overview of potential risks and mitigationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Stress Testing Chain-of-Thought Prompting for Large Language Models
  2. 2022Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters
  3. 2024To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
  4. 2024Unveiling the Statistical Foundations of Chain-of-Thought Prompting Methods
  5. 2024The Impact of Reasoning Step Length on Large Language Models
  6. 2025Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens
  7. 2023Towards Better Chain-of-Thought Prompting Strategies: A Survey
  8. 2024Chain-of-Thought Reasoning Without Prompting