Understanding and Mitigating Premature Confidence for Better LLM Reasoning

• URL: http://arxiv.org/abs/2605.24396v1
• Date: Sat, 23 May 2026 04:42:45 GMT
• Title: Understanding and Mitigating Premature Confidence for Better LLM Reasoning
• Abstract summary: Long chains of thought (CoT) from current language models frequently contain logical gaps and unjustified leaps.<n>We find such a signal in how the model's confidence evolves during reasoning.<n>We exploit this in progressive confidence shaping, a reinforcement learning objective that trains models to update their confidence as they reason rather than commit early.
• Score: 76.16007941549857
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Long chains of thought (CoT) from current language models frequently contain logical gaps and unjustified leaps, limiting the gains from additional test-time compute. Improving reasoning quality directly would require process reward models, but the step-level annotations needed to train them are expensive and scarce. We find such a signal in how the model's confidence evolves during reasoning: premature confidence, the tendency to commit to an answer early and use the remaining tokens to rationalize it, strongly predicts flawed reasoning across tasks and model scales. We exploit this in progressive confidence shaping, a reinforcement learning objective that trains models to update their confidence as they reason rather than commit early -- rewarding gradual confidence growth and penalizing early commitment, with no external labels or reward models. The method improves accuracy and reasoning quality from 1.5B to 8B parameters across arithmetic (Countdown), math (DAPO, AIME), and science (ScienceQA): on Countdown, accuracy improves 3.2x (+42.0pp) and flawed reasoning drops 48pp; on AIME, Pass@64 improves 6.6pp. Consistent with this mechanism, the method also improves faithfulness: on a safety benchmark, our models more transparently surface misleading content in their reasoning traces rather than concealing it. Controlled experiments reveal that the problem and its remedy scale together: premature confidence grows with model size and task difficulty, and so do the gains from addressing it.

Related papers

• Does Reasoning Preserve Alignment? On the Trustworthiness of Large Reasoning Models [55.788110316999166]
  We compare reasoning models produced via supervised fine-tuning, RL-based post-training, and distillation against instruction-tuned baselines.<n>We observe that reasoning models often improve on reasoning benchmarks but exhibit alignment regressions.<n>These regressions are consistent with behavioral drift from the instruction-tuned baseline, measured by KL divergence.
  arXiv  Detail & Related papers  (2026-06-09T16:14:27Z)
• Confidence-Orchestrated Self-Evolution against Uncertain LLM Feedback [8.780008955074967]
  Self-evolving large language models (LLMs) learn by generating their own training tasks and solutions, reducing reliance on human-curated supervision.<n>We propose COSE (Confidence-Orchestrated Self-Evolution), which uses the LLM's intrinsic confidence as a lightweight uncertainty signal to modulate learning.
  arXiv  Detail & Related papers  (2026-05-27T06:07:10Z)
• Confidence-Aware Alignment Makes Reasoning LLMs More Reliable [65.44962502963378]
  We introduce CASPO, a framework that aligns token-level confidence with step-wise logical correctness without training a separate reward model.<n>During inference, we propose Confidence-aware Thought (CaT), which dynamically prunes uncertain reasoning branches with negligible O(V) latency.<n>Experiments across ten benchmarks and multiple model families show that CASPO consistently improves reasoning reliability and inference efficiency.
  arXiv  Detail & Related papers  (2026-05-08T07:08:25Z)
• Early Stopping for Large Reasoning Models via Confidence Dynamics [55.67938134245981]
  Large reasoning models rely on long chain-of-thought generation to solve complex problems.<n>Key challenge is determining when the model should stop reasoning and produce the final answer.<n>We propose CoDE-Stop, an early stopping method that leverages the dynamics of intermediate answer confidence to decide when to terminate reasoning.
  arXiv  Detail & Related papers  (2026-04-06T17:59:45Z)
• Thinking, Faithful and Stable: Mitigating Hallucinations in LLMs [0.4115305983711515]
  This project develops a self correcting framework for large language models (LLMs)<n>Rather than relying solely on final answer correctness, our approach leverages fine grained uncertainty signals.<n>We design a composite reward function that penalizes unjustified high confidence and entropy spikes.
  arXiv  Detail & Related papers  (2025-11-19T23:09:26Z)
• Think Just Enough: Sequence-Level Entropy as a Confidence Signal for LLM Reasoning [5.37133760455631]
  We introduce a novel entropy-based framework to drive token efficiency in large language models during reasoning tasks.<n>Our approach uses Shannon entropy from token-level logprobs as a confidence signal to enable early stopping.<n>We show that entropy-based confidence calibration represents an emergent property of advanced post-training optimization.
  arXiv  Detail & Related papers  (2025-10-09T12:33:16Z)
• Your Models Have Thought Enough: Training Large Reasoning Models to Stop Overthinking [50.97239453902612]
  Large Reasoning Models (LRMs) have achieved impressive performance on challenging tasks, yet their deep reasoning often incurs substantial computational costs.<n>Inspired by Evidence Accumulation Models, we find that LRMs have accumulated sufficient information early in reasoning, making further reasoning steps redundant.<n>We propose Just-Enough Thinking (JET), which trains models to proactively terminate unnecessary reasoning.
  arXiv  Detail & Related papers  (2025-09-27T16:25:06Z)
• ConfTuner: Training Large Language Models to Express Their Confidence Verbally [58.63318088243125]
  Large Language Models (LLMs) are increasingly deployed in high-stakes domains such as science, law, and healthcare.<n>LLMs are often observed to generate incorrect answers with high confidence, a phenomenon known as "overconfidence"
  arXiv  Detail & Related papers  (2025-08-26T09:25:32Z)
• 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)
• Reasoning Models Better Express Their Confidence [43.29929311958733]
  Large language models (LLMs) often fail to communicate their confidence accurately.<n>We demonstrate that reasoning models that engage in extended chain-of-thought (CoT) reasoning exhibit superior performance.
  arXiv  Detail & Related papers  (2025-05-20T15:19:00Z)

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.