mlsanityData to 14 Oct 2026

Understanding Chain-of-Thought in LLMs through Information Theory

arXiv 2411.11984 ↗First posted 18 Nov 2024cs.CL cs.AI cs.LGcited by 37

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

Abstract (arXiv)

Large Language Models (LLMs) have shown impressive performance in complex reasoning tasks through the use of Chain-of-Thought (CoT) reasoning, allowing models to break down problems into manageable sub-tasks. However, existing CoT evaluation techniques either require annotated CoT data or fall short in accurately assessing intermediate reasoning steps, leading to high rates of false positives. In this paper, we formalize CoT reasoning in LLMs through an information-theoretic lens. Specifically, our framework quantifies the `information-gain' at each reasoning step, enabling the identification of failure modes in LLMs without the need for expensive annotated datasets. We demonstrate the efficacy of our approach through extensive experiments on toy arithmetic, GSM8K and PRM800k datasets, where it significantly outperforms existing outcome-based methods by providing more accurate insights into model performance on individual subtasks.

Key facts. Cited by 37 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 16 of its 37 references that are in the map. First posted on arXiv 18 Nov 2024.

Builds on

16 of 37 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Chain of Thought Empowers Transformers to Solve Inherently Serial Problems20 Feb

Other references · 15

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  5. 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
  6. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  7. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,822
  8. 2023PaLM 2 Technical Reportcited by 1,162
  9. 2023Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotationscited by 928
  10. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 886
  11. 2019MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalismscited by 662
  12. 2022Impact of Pretraining Term Frequencies on Few-Shot Reasoningcited by 142
3 more
  1. 2020LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoningcited by 69
  2. 2024Multi-step Problem Solving Through a Verifier: An Empirical Analysis on Model-induced Process Supervisioncited by 52
  3. 2023Beyond Words: A Mathematical Framework for Interpreting Large Language Modelscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 23; 2026: 14.

37 papers.

Sort:

By area:

  1. 2025When More is Less: Understanding Chain-of-Thought Length in LLMscited by 183
  2. 2025CoT-Valve: Length-Compressible Chain-of-Thought Tuningcited by 169
  3. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 126
  4. 2025Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoningcited by 51
  5. 2025Rethinking External Slow-Thinking: From Snowball Errors to Probability of Correct Reasoningcited by 36
  6. 2025Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lenscited by 34
  7. 2025Benchmarking Reasoning Robustness in Large Language Modelscited by 30
  8. 2025Entropy-based Exploration Conduction for Multi-step Reasoningcited by 29
  9. 2026Understanding Agent Scaling in LLM-Based Multi-Agent Systems via Diversitycited by 29
  10. 2025Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Modelscited by 25
  11. 2025Entropy After </Think> for reasoning model early exitingcited by 24
  12. 2025Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoningcited by 17
25 more
  1. 2025Unlocking the Power of Multi-Agent LLM for Reasoning: From Lazy Agents to Deliberationcited by 11
  2. 2025PiCSAR: Probabilistic Confidence Selection And Ranking for Reasoning Chainscited by 10
  3. 2026Analyzing and Improving Chain-of-Thought Monitorability Through Information Theorycited by 10
  4. 2026Understanding Reasoning in LLMs through Strategic Information Allocation under Uncertaintycited by 9
  5. 2025Translate Policy to Language: Flow Matching Generated Rewards for LLM Explanationscited by 6
  6. 2025Reasoning or Overthinking: Evaluating Large Language Models on Financial Sentiment Analysiscited by 6
  7. 2025Beyond In-Distribution Success: Scaling Curves of CoT Granularity for Language Model Generalizationcited by 5
  8. 2025Decoupling Knowledge and Reasoning in LLMs: An Exploration Using Cognitive Dual-System Theorycited by 5
  9. 2025PRInTS: Reward Modeling for Long-Horizon Information Seekingcited by 5
  10. 2025Reasoning Can Hurt the Inductive Abilities of Large Language Modelscited by 4
  11. 2025Why Does Reasoning Length Converge? Unveiling the Underfitting-Overfitting Trade-off in Chain-of-Thoughtcited by 4
  12. 2025Pinpointing crucial steps: Attribution-based Credit Assignment for Verifiable Reinforcement Learningcited by 4
  13. 2026The Stepwise Informativeness Assumption: Why are Entropy Dynamics and Reasoning Correlated in LLMs?cited by 3
  14. 2026How Far Ahead Do LLMs Plan? Uncovering the Latent Horizon in Chain-of-Thought Reasoningcited by 2
  15. 2026GRACE: Step-Level Benchmark for Faithful Reasoning over Contextcited by 2
  16. 2025Understanding Generalization in Role-Playing Models via Information Theorycited by 1
  17. 2026SCA: Segment-Wise CoT Compression with Answer Alignmentcited by 1
  18. 2026Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneckcited by 1
  19. 2026Beyond the Prompt in Large Language Models: Comprehension, In-Context Learning, and Chain-of-Thoughtcited by 1
  20. 2026Answer-Distribution Trajectories: A Stochastic-Dynamics View of LLM Reasoningcited by 1
  21. 2025Probing Geometry of Next Token Prediction Using Cumulant Expansion of the Softmax Entropycited by 0
  22. 2026Process Supervision for Chain-of-Thought Reasoning via Monte Carlo Net Information Gaincited by 0
  23. 2026When Less is Enough: Efficient Inference via Collaborative Reasoningcited by 0
  24. 2026Interpreting Reasoning of Large Language Models via Partial Information Decompositioncited by 0
  25. 2026To Explore The Strange New World Beyond Data Distribution: System Behavior, Causality Tax, and Non-causal Base Modelcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024LLMs Faithfully and Iteratively Compute Answers During CoT: A Systematic Analysis With Multi-step Arithmetics
  2. 2026The Tell-Tale Trace: Detecting Reasoning Failures in LLMs Using Chain-of-Thought Dynamics
  3. 2025Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens
  4. 2026Hierarchical Chain-of-Thought: Enhancing LLM Reasoning Performance and Efficiency
  5. 2024Strategic Chain-of-Thought: Guiding Accurate Reasoning in LLMs through Strategy Elicitation
  6. 2023Chain-of-Thought Hub: A Continuous Effort to Measure Large Language Models' Reasoning Performance
  7. 2024Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs
  8. 2025The CoT Encyclopedia: Analyzing, Predicting, and Controlling how a Reasoning Model will Think