mlsanityData to 7 Oct 2026

A Hopfieldian View-based Interpretation for Chain-of-Thought Reasoning

arXiv 2406.12255 ↗First posted 18 Jun 2024cs.CL cs.AI cs.HCcited by 15

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

Abstract (arXiv)

Chain-of-Thought (CoT) holds a significant place in augmenting the reasoning performance for large language models (LLMs). While some studies focus on improving CoT accuracy through methods like retrieval enhancement, yet a rigorous explanation for why CoT achieves such success remains unclear. In this paper, we analyze CoT methods under two different settings by asking the following questions: (1) For zero-shot CoT, why does prompting the model with "let's think step by step" significantly impact its outputs? (2) For few-shot CoT, why does providing examples before questioning the model could substantially improve its reasoning ability? To answer these questions, we conduct a top-down explainable analysis from the Hopfieldian view and propose a Read-and-Control approach for controlling the accuracy of CoT. Through extensive experiments on seven datasets for three different tasks, we demonstrate that our framework can decipher the inner workings of CoT, provide reasoning error localization, and control to come up with the correct reasoning path.

Key facts. Cited by 15 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 34 of its 86 references that are in the map. First posted on arXiv 18 Jun 2024.

Builds on

34 of 86 references.

Closest ancestors · 7

Same direction, newest first

  1. 2024Chain of Thoughtlessness? An Analysis of CoT in Planning8 May
  2. 2024Let's Think Dot by Dot: Hidden Computation in Transformer Language Models24 Apr
  3. 2024How to think step-by-step: A mechanistic understanding of chain-of-thought reasoning28 Feb
  4. 2024Chain-of-Thought Reasoning Without Prompting15 Feb
  5. 2024The Impact of Reasoning Step Length on Large Language Models10 Jan
  6. 2023The Expressive Power of Transformers with Chain of Thought11 Oct
  7. 2023Measuring Faithfulness in Chain-of-Thought Reasoning17 Jul

Other references · 27

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  2. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  5. 2023Mistral 7Bcited by 3,065
  6. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  7. 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,239
  8. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,199
  9. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  10. 2022In-context Learning and Induction Headscited by 930
  11. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 871
  12. 2023The Linear Representation Hypothesis and the Geometry of Large Language Modelscited by 679
15 more
  1. 2024ReFT: Representation Finetuning for Language Modelscited by 186
  2. 2023Multilingual Machine Translation with Large Language Models: Empirical Results and Analysiscited by 156
  3. 2022Rethinking with Retrieval: Faithful Large Language Model Inferencecited by 145
  4. 2022Faithful Reasoning Using Large Language Modelscited by 130
  5. 2023Large Language Models are In-Context Semantic Reasoners rather than Symbolic Reasonerscited by 63
  6. 2024MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learningcited by 63
  7. 2023Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Codecited by 62
  8. 2024Multi-hop Question Answering under Temporal Knowledge Editingcited by 36
  9. 2024Editable Concept Bottleneck Modelscited by 22
  10. 2023Differentially Private Natural Language Models: Recent Advances and Future Directionscited by 20
  11. 2023Improving Interpretation Faithfulness for Vision Transformerscited by 12
  12. 2024Text Guided Image Editing with Automatic Concept Locating and Forgettingcited by 12
  13. 2024Dialectical Alignment: Resolving the Tension of 3H and Security Threats of LLMscited by 11
  14. 2024Leveraging Logical Rules in Knowledge Editing: A Cherry on the Topcited by 11
  15. 2024MONAL: Model Autophagy Analysis for Modeling Human-AI Interactionscited by 7

Built on by

Cited by year (2026 to 7 Oct)

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

15 papers.

Sort:

By area:

  1. 2025When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Modelscited by 46
  2. 2024Semi-supervised Concept Bottleneck Modelscited by 21
  3. 2025Adaptive Multi-Subspace Representation Steering for Attribute Alignment in Large Language Modelscited by 16
  4. 2025Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoningcited by 11
  5. 2024MQA-KEAL: Multi-hop Question Answering under Knowledge Editing for Arabic Languagecited by 9
  6. 2024Towards Multi-dimensional Explanation Alignment for Medical Classificationcited by 6
  7. 2025COMPKE: Complex Question Answering under Knowledge Editingcited by 6
  8. 2026Controlling Repetition in Protein Language Modelscited by 4
  9. 2026Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and Stabilitycited by 4
  10. 2024Faithful Interpretation for Graph Neural Networkscited by 3
  11. 2025Stable Vision Concept Transformers for Medical Diagnosiscited by 3
  12. 2025Towards Reasoning-Preserving Unlearning in Multimodal Large Language Modelscited by 2
3 more
  1. 2026Understanding the Dynamics of Demonstration Conflict in In-Context Learningcited by 2
  2. 2025OncoReason: Structuring Clinical Reasoning in LLMs for Robust and Interpretable Survival Predictioncited by 1
  3. 2026Multi-Adapter Representation Interventions via Energy Calibrationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Understanding Reasoning in Chain-of-Thought from the Hopfieldian View
  2. 2025Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning
  3. 2025The CoT Encyclopedia: Analyzing, Predicting, and Controlling how a Reasoning Model will Think
  4. 2024Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs
  5. 2024Unlocking the Capabilities of Thought: A Reasoning Boundary Framework to Quantify and Optimize Chain-of-Thought
  6. 2024Understanding Chain-of-Thought in LLMs through Information Theory
  7. 2026Stateful Reasoning via Insight Replay
  8. 2022Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters