Revisiting Overthinking in Long Chain-of-Thought from the Perspective of Self-Doubt

• URL: http://arxiv.org/abs/2505.23480v1
• Date: Thu, 29 May 2025 14:30:02 GMT
• Title: Revisiting Overthinking in Long Chain-of-Thought from the Perspective of Self-Doubt
• Authors: Keqin Peng, Liang Ding, Yuanxin Ouyang, Meng Fang, Dacheng Tao,
• Abstract summary: Reasoning Large Language Models (RLLMs) have demonstrated impressive performance on complex tasks.<n>They often exhibit overthinking -- performing unnecessary reasoning steps even after arriving at the correct answer.<n>We present a quantitative analysis of overthinking from the perspective of self-doubt.<n>We introduce a simple and effective prompting method to reduce the model's over-reliance on input questions.
• Score: 74.35891434097053
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reasoning Large Language Models (RLLMs) have demonstrated impressive performance on complex tasks, largely due to the adoption of Long Chain-of-Thought (Long CoT) reasoning. However, they often exhibit overthinking -- performing unnecessary reasoning steps even after arriving at the correct answer. Prior work has largely focused on qualitative analyses of overthinking through sample-based observations of long CoTs. In contrast, we present a quantitative analysis of overthinking from the perspective of self-doubt, characterized by excessive token usage devoted to re-verifying already-correct answer. We find that self-doubt significantly contributes to overthinking. In response, we introduce a simple and effective prompting method to reduce the model's over-reliance on input questions, thereby avoiding self-doubt. Specifically, we first prompt the model to question the validity of the input question, and then respond concisely based on the outcome of that evaluation. Experiments on three mathematical reasoning tasks and four datasets with missing premises demonstrate that our method substantially reduces answer length and yields significant improvements across nearly all datasets upon 4 widely-used RLLMs. Further analysis demonstrates that our method effectively minimizes the number of reasoning steps and reduces self-doubt.

Related papers

• Think How to Think: Mitigating Overthinking with Autonomous Difficulty Cognition in Large Reasoning Models [12.618562275265704]
  Recent Large Reasoning Models (LRMs) excel at complex reasoning tasks but often suffer from overthinking.<n>We propose Think-How-to-Think (TH2T), a novel two-stage fine-tuning strategy that progressively inspires LRMs' difficulty cognition and redundancy cognition.
  arXiv  Detail & Related papers  (2025-07-03T14:24:26Z)
• Does Thinking More always Help? Understanding Test-Time Scaling in Reasoning Models [103.03315678501546]
  Extending thinking traces using prompts like "Wait" or "Let me rethink" can improve performance.<n>This raises a natural question: Does thinking more at test-time truly lead to better reasoning?<n>We show a consistent pattern of initial performance improvements from additional thinking followed by a decline, due to "overthinking"
  arXiv  Detail & Related papers  (2025-06-04T17:55:09Z)
• Answer Convergence as a Signal for Early Stopping in Reasoning [7.60104447055814]
  Chain-of-thought (CoT) prompting enhances reasoning in large language models (LLMs)<n>We propose three inference-time strategies to improve efficiency: (1) early stopping via answer consistency, (2) boosting the probability of generating end-of-reasoning signals, and (3) a supervised method that learns when to stop based on internal activations.
  arXiv  Detail & Related papers  (2025-06-03T07:20:54Z)
• Let LLMs Break Free from Overthinking via Self-Braking Tuning [60.08396797526657]
  Large reasoning models (LRMs) have significantly enhanced their reasoning capabilities by generating longer chains of thought.<n>This performance gain comes at the cost of a substantial increase in redundant reasoning during the generation process.<n>We propose a novel framework, Self-Braking Tuning (SBT), which tackles overthinking from the perspective of allowing the model to regulate its own reasoning process.
  arXiv  Detail & Related papers  (2025-05-20T16:53:40Z)
• Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs [52.405085773954596]
  We find that large language models (LLMs) tend to overthink simple problems, generating unnecessarily long outputs, and underthink harder ones.<n>This indicates that models might misjudge problem difficulty and fail to calibrate their response length appropriately.<n> Experiments show that the generation length can be significantly reduced while maintaining acceptable accuracy.
  arXiv  Detail & Related papers  (2025-04-30T18:48:06Z)
• Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think [51.0691253204425]
  We analyze intermediate reasoning steps, termed subthoughts, to answer two questions: Does the final answer reliably represent the model's optimal conclusion?<n>Our approach involves segmenting a reasoning trace into sequential subthoughts based on linguistic cues.<n>We find that aggregating these answers by selecting the most frequent one (the mode) often yields significantly higher accuracy compared to relying solely on the answer derived from the original complete trace.
  arXiv  Detail & Related papers  (2025-04-29T12:39:07Z)
• Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill? [27.374491920521745]
  We find that the response length of reasoning LLMs drastically increases for ill-posed questions with missing premises (MiP)<n>This newly introduced scenario exacerbates the general overthinking issue to a large extent, which we name as the MiP-Overthinking.<n>Surprisingly, LLMs not specifically trained for reasoning exhibit much better performance on the MiP scenario, producing much shorter responses that quickly identify ill-posed queries.
  arXiv  Detail & Related papers  (2025-04-09T01:25:27Z)
• Think When You Need: Self-Adaptive Chain-of-Thought Learning [20.22448368125018]
  Chain of Thought (CoT) reasoning enhances language models' performance but often leads to inefficient "overthinking" on simple problems.<n>We identify that existing approaches directly penalizing reasoning length fail to account for varying problem complexity.<n>Our approach constructs rewards through length and quality comparisons, guided by theoretical assumptions that jointly enhance solution correctness with conciseness.
  arXiv  Detail & Related papers  (2025-04-04T07:34:01Z)
• Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs [86.79757571440082]
  Large language models (LLMs) such as OpenAI's o1 have demonstrated remarkable abilities in complex reasoning tasks.<n>We identify a phenomenon we term underthinking, where o1-like LLMs frequently switch between different reasoning thoughts.<n>We propose a decoding strategy with thought switching penalty TIP that discourages premature transitions between thoughts.
  arXiv  Detail & Related papers  (2025-01-30T18:58:18Z)
• Self-Contradictory Reasoning Evaluation and Detection [31.452161594896978]
  We investigate self-contradictory (Self-Contra) reasoning, where the model reasoning does not support its answers. We find that LLMs often contradict themselves in reasoning tasks involving contextual information understanding or commonsense. We find that GPT-4 can detect Self-Contra with a 52.2% F1 score, much lower compared to 66.7% for humans.
  arXiv  Detail & Related papers  (2023-11-16T06:22:17Z)

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.