Can Aha Moments Be Fake? Identifying True and Decorative Thinking Steps in Chain-of-Thought

• URL: http://arxiv.org/abs/2510.24941v1
• Date: Tue, 28 Oct 2025 20:14:02 GMT
• Title: Can Aha Moments Be Fake? Identifying True and Decorative Thinking Steps in Chain-of-Thought
• Authors: Jiachen Zhao, Yiyou Sun, Weiyan Shi, Dawn Song,
• Abstract summary: Large language models (LLMs) can generate long Chain-of-Thought (CoT) at test time, enabling them to solve complex tasks.<n>We measure the step-wise causal influence of each reasoning step on the model's final prediction with a proposed True Thinking Score (TTS)<n>We identify a TrueThinking direction in the latent space of LLMs, which can force the model to perform or disregard certain CoT steps.
• Score: 72.45900226435289
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent large language models (LLMs) can generate long Chain-of-Thought (CoT) at test time, enabling them to solve complex tasks. These reasoning steps in CoT are often assumed as a faithful reflection of the model's internal thinking process, and used to monitor unsafe intentions. However, we find many reasoning steps don't truly contribute to LLMs' prediction. We measure the step-wise causal influence of each reasoning step on the model's final prediction with a proposed True Thinking Score (TTS). We reveal that LLMs often interleave between true-thinking steps (which are genuinely used to produce the final output) and decorative-thinking steps (which only give the appearance of reasoning but have minimal causal impact). Notably, only a small subset of the total reasoning steps have a high TTS that causally drive the model's prediction: e.g., for the AIME dataset, only an average of 2.3% of reasoning steps in CoT have a TTS >= 0.7 (range: 0-1) under the Qwen-2.5 model. Furthermore, we identify a TrueThinking direction in the latent space of LLMs. By steering along or against this direction, we can force the model to perform or disregard certain CoT steps when computing the final result. Finally, we highlight that self-verification steps in CoT (i.e., aha moments) can also be decorative, where LLMs do not truly verify their solution. Steering along the TrueThinking direction can force internal reasoning over these steps, resulting in a change in the final results. Overall, our work reveals that LLMs often verbalize reasoning steps without actually performing them internally, which undermines both the efficiency of LLM reasoning and the trustworthiness of CoT.

Related papers

• No Global Plan in Chain-of-Thought: Uncover the Latent Planning Horizon of LLMs [65.783709850324]
  This work stems from prior complementary observations on the dynamics of Chain-of-Thought (CoT): Large Language Models (LLMs)<n>LLMs are shown latent planning of subsequent reasoning prior to CoT emergence, thereby diminishing the significance of explicit CoT.<n>We investigate the latent planning strength of LLMs, through our probing method, Tele-Lens, applying to hidden states across diverse task domains.
  arXiv  Detail & Related papers  (2026-02-02T13:46:56Z)
• Reason-KE++: Aligning the Process, Not Just the Outcome, for Faithful LLM Knowledge Editing [63.96040994220329]
  We find that SFT-based methods, e.g., Reason-KE, suffer from a "faithfulness gap"<n>This gap enables the LLM's powerful parametric priors to override new contextual facts.<n>We propose Reason-KE++, an SFT+RL framework that instills process-level faithfulness.
  arXiv  Detail & Related papers  (2025-11-16T15:49:01Z)
• Reasoning with Confidence: Efficient Verification of LLM Reasoning Steps via Uncertainty Heads [104.9566359759396]
  We propose a lightweight alternative for step-level reasoning verification based on data-driven uncertainty scores.<n>Our findings suggest that the internal states of LLMs encode their uncertainty and can serve as reliable signals for reasoning verification.
  arXiv  Detail & Related papers  (2025-11-09T03:38:29Z)
• Stop Spinning Wheels: Mitigating LLM Overthinking via Mining Patterns for Early Reasoning Exit [114.83867400179354]
  Overthinking can degrade overall performance of large language models.<n>We categorize reasoning into three stages: insufficient exploration stage, compensatory reasoning stage, and reasoning convergence stage.<n>We develop a lightweight thresholding strategy based on rules to improve reasoning accuracy.
  arXiv  Detail & Related papers  (2025-08-25T03:17:17Z)
• Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts [79.1081247754018]
  Large Language Models (LLMs) are widely deployed in reasoning, planning, and decision-making tasks.<n>We propose a framework based on Contact Searching Questions(CSQ) to quantify the likelihood of deception.
  arXiv  Detail & Related papers  (2025-08-08T14:46:35Z)
• Overclocking LLM Reasoning: Monitoring and Controlling Thinking Path Lengths in LLMs [52.663816303997194]
  A key factor influencing answer quality is the length of the thinking stage.<n>This paper explores and exploits the mechanisms by which LLMs understand and regulate the length of their reasoning.<n>Our results demonstrate that this "overclocking" method mitigates overthinking, improves answer accuracy, and reduces inference latency.
  arXiv  Detail & Related papers  (2025-06-08T17:54:33Z)
• The Price of a Second Thought: On the Evaluation of Reasoning Efficiency in Large Language Models [54.88805865447848]
  We show that instruct models achieve higher efficiency overall, and problem difficulty affects efficiency.<n>We propose COTHINK, a simple two-stage pipeline: an instruct model drafts a brief outline, and a thinking model expands it.<n>On GSM8K, MATH500, and AIME24, COTHINK cuts token usage by 21.1% while keeping accuracy on four thinking models, and remains competitive with strong efficiency baselines.
  arXiv  Detail & Related papers  (2025-05-28T06:24:45Z)
• Have Large Language Models Learned to Reason? A Characterization via 3-SAT Phase Transition [11.422434149376478]
  Large Language Models (LLMs) have been touted as AI models possessing advanced reasoning abilities.<n>In theory, autoregressive LLMs with Chain-of-Thought (CoT) can perform more serial computations to solve complex reasoning tasks.<n>Recent studies suggest that, despite this capacity, LLMs do not truly learn to reason but instead fit on statistical features.
  arXiv  Detail & Related papers  (2025-04-04T20:57:36Z)
• SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs [48.28847964704554]
  Chain-of-Thought (CoT) reasoning enables Large Language Models (LLMs) to solve complex reasoning tasks.<n>We propose a novel approach for continuous-space reasoning that does not require modifying the LLM.
  arXiv  Detail & Related papers  (2025-02-17T18:52:29Z)
• When More is Less: Understanding Chain-of-Thought Length in LLMs [51.631483479081645]
  Large Language Models (LLMs) employ Chain-of-Thought (CoT) reasoning to deconstruct complex problems.<n>This paper argues that longer CoTs are often presumed superior, arguing that longer is not always better.
  arXiv  Detail & Related papers  (2025-02-11T05:28:59Z)
• Premise-Augmented Reasoning Chains Improve Error Identification in Math reasoning with LLMs [10.179253284788796]
  Chain-of-Thought (CoT) prompting enhances mathematical reasoning in large language models (LLMs)<n>We present a framework that identifies the premises for each step, to improve the evaluation of reasoning.<n>Our findings highlight the utility of premise-centric representations in addressing complex problem-solving tasks.
  arXiv  Detail & Related papers  (2025-02-04T14:44:58Z)
• Assessing Step-by-Step Reasoning against Lexical Negation: A Case Study on Syllogism [19.590120229602103]
  Large language models (LLMs) take advantage of step-by-step reasoning instructions, e.g., chain-of-thought (CoT) prompting. In this study, we inspect the step-by-step reasoning ability of LLMs with a focus on negation.
  arXiv  Detail & Related papers  (2023-10-23T12:40:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.