mlsanityData to 14 Oct 2026

Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation?

arXiv 2508.19827 ↗First posted 27 Aug 2025cs.AI cs.CLcited by 9

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

Abstract (arXiv)

Recent work has demonstrated that Chain-of-Thought (CoT) often yields limited gains for soft-reasoning problems such as analytical and commonsense reasoning. CoT can also be unfaithful to a model's actual reasoning. We investigate the dynamics and faithfulness of CoT in soft-reasoning tasks across instruction-tuned, reasoning and reasoning-distilled models. Our findings reveal differences in how these models rely on CoT, and show that CoT influence and faithfulness are not always aligned.

Key facts. Cited by 9 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 35 references that are in the map. First posted on arXiv 27 Aug 2025.

Builds on

10 of 35 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Chain-of-Thought Reasoning In The Wild Is Not Always Faithful11 Mar
  2. 2025Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps20 Feb
  3. 2024Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse27 Oct
  4. 2023Measuring Faithfulness in Chain-of-Thought Reasoning17 Jul

Other references · 6

  1. 2025Qwen3 Technical Reportcited by 8,820
  2. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  3. 2024Qwen2.5 Technical Reportcited by 4,942
  4. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,737
  5. 2025Are DeepSeek R1 And Other Reasoning Models More Faithful?cited by 72
  6. 2025Truthful or Fabricated? Using Causal Attribution to Mitigate Reward Hacking in Explanationscited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 9.

9 papers.

  1. 2026Where does output diversity collapse in post-training?cited by 11
  2. 2026Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluationcited by 7
  3. 2026Phantom Guardrails: When Self-Improving Agent Harnesses Fix Failures That Never Happenedcited by 7
  4. 2026Large Language Model Agents Are Not Always Faithful Self-Evolverscited by 5
  5. 2026Measuring and Mitigating Post-hoc Rationalization in Reverse Chain-of-Thought Generationcited by 2
  6. 2026Unreal Thinking: Chain-of-Thought Hijacking via Two-stage Backdoorcited by 2
  7. 2026Opening the Black Box: A Survey on the Mechanisms of Multi-Step Reasoning in Large Language Modelscited by 1
  8. 2026Faithful or Fabricated? A Causal Framework for Rationalization Bias in LLM Judgescited by 0
  9. 2026From Plausible to Actionable: A Position on LLM Self-Explanationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Can Aha Moments Be Fake? Towards Quantifying Decorative and True Thinking in Chain-of-Thought
  2. 2026Lie to Me: How Faithful Is Chain-of-Thought Reasoning in Reasoning Models?
  3. 2026When does Chain-of-Thought Help: A Markovian Perspective
  4. 2024Unlocking the Capabilities of Thought: A Reasoning Boundary Framework to Quantify and Optimize Chain-of-Thought
  5. 2025CoT is Not True Reasoning, It Is Just a Tight Constraint to Imitate: A Theory Perspective
  6. 2025Explainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning Dynamics
  7. 2026Post-Hoc Reasoning in Chain of Thought: Decoding and Steering Pre-Committed Answers
  8. 2026Mechanistic Evidence for Faithfulness Decay in Chain-of-Thought Reasoning