Calibration Drift Under Reasoning: How Chain-of-Thought Budgets Induce Overconfidence in Large Language Models

• URL: http://arxiv.org/abs/2606.11211v1
• Date: Fri, 24 Apr 2026 04:46:16 GMT
• Title: Calibration Drift Under Reasoning: How Chain-of-Thought Budgets Induce Overconfidence in Large Language Models
• Abstract summary: Chain-of-thought (CoT) reasoning is widely used to improve accuracy and reliability.<n>We show that increasing the reasoning budget beyond a task-specific threshold can cause models to become systematically overconfident.<n>We propose a Hypothesis Lock-In model based on autoregressive generation to explain this behavior.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The ability of large language models (LLMs) to express calibrated uncertainty is important for safe deployment. Chain-of-thought (CoT) reasoning is widely used to improve accuracy and reliability, but its effect on calibration is not fully understood. We show that this picture is incomplete: in some settings, increasing the reasoning budget beyond a task-specific threshold can cause models to become systematically overconfident, assigning high confidence to incorrect answers. We call this phenomenon Calibration Drift Under Reasoning (CDUR) and study it both theoretically and empirically. We define reasoning budget B and analyze conditions under which Expected Calibration Error ECE(B) follows a non-monotonic pattern: it first decreases as reasoning corrects errors, then increases as longer reasoning produces internally consistent but incorrect explanations. We propose a Hypothesis Lock-In model based on autoregressive generation to explain this behavior. We evaluate Llama-3.1-8B and Llama-3.3-70B on 47 reasoning-trap questions across four reasoning budgets and three seeds (1,368 API calls; 574 valid responses). The 8B model shows non-monotonic calibration behavior, while results for the 70B model are limited to baseline evaluation and are inconclusive for budget-dependent effects. We introduce CABStop, a calibration-aware stopping rule that halts reasoning when confidence diverges from an auxiliary accuracy estimate. These results suggest that increasing reasoning depth does not always improve reliability and should be monitored carefully.

Related papers

• Amplified Does Not Mean Predictive: Reasoning Behaviors in Thinking Models [56.88565331713778]
  reasoning-oriented training can make traces look more deliberative without amplifying the behaviors most tied to model correctness.<n>We quantify this mismatch with Behavioral Lift, a metric that measures how much correctness changes when a behavior is present versus absent in a model's reasoning trace.<n>We find evidence for an Amplification-Lift Gap, in which thinking models strongly amplify self-awareness, hypothesis testing, and uncertainty acknowledgment.
  arXiv  Detail & Related papers  (2026-08-13T20:37:59Z)
• 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)
• Understanding and Mitigating Premature Confidence for Better LLM Reasoning [76.16007941549857]
  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.
  arXiv  Detail & Related papers  (2026-05-23T04:42:45Z)
• Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models [94.68358825189738]
  We propose a post-training framework for verifiable domains that jointly optimize prediction accuracy and reasoning quality.<n>We evaluate VPS on chess, a controlled testbed where reasoning steps can be deterministically verified against engine signals.<n>VPS preserves accuracy while significantly improving reasoning quality, reducing win-rate error by up to 30% and restoring consistency to near saturation.
  arXiv  Detail & Related papers  (2026-04-03T15:19:46Z)
• On Calibration of Large Language Models: From Response To Capability [66.59139960234326]
  Large language models (LLMs) are widely deployed as general-purpose problem solvers.<n>We introduce capability calibration, which targets the model's expected accuracy on a query.<n>Our results demonstrate that capability-calibrated confidence improves pass@$k$ prediction and inference budget allocation.
  arXiv  Detail & Related papers  (2026-02-14T01:07:45Z)
• EpiCaR: Knowing What You Don't Know Matters for Better Reasoning in LLMs [9.412828452977553]
  Existing approaches reinforce successful reasoning paths, incurring a substantial calibration cost.<n>This failure has been characterized as a form of model collapse in alignment.<n>We proposeEpiCaR as a training objective that jointly optimize reasoning performance and calibration.
  arXiv  Detail & Related papers  (2026-01-11T06:21:13Z)
• Mitigating LLM Hallucination via Behaviorally Calibrated Reinforcement Learning [32.32593439144886]
  Behavior-calibrated reinforcement learning allows smaller models to surpass frontier models in uncertainty quantification.<n>Our model's log-scale Accuracy-to-Hallucination Ratio gain (0.806) exceeds GPT-5's (0.207) in a challenging in-domain evaluation.
  arXiv  Detail & Related papers  (2025-12-22T22:51:48Z)
• Compressed Causal Reasoning: Quantization and GraphRAG Effects on Interventional and Counterfactual Accuracy [0.0]
  This study systematically evaluate quantization effects across all three levels of Pearls Causal Ladder.<n>We find that rung level accuracy in Llama 3 8B remains broadly stable under quantization, with NF4 showing less than one percent overall degradation.<n>Experiments on the CRASS benchmark show near identical performance across precisions, indicating that existing commonsense counterfactual datasets lack the structural sensitivity needed to reveal quantization induced reasoning drift.
  arXiv  Detail & Related papers  (2025-12-13T17:54:15Z)
• Reasoning about Uncertainty: Do Reasoning Models Know When They Don't Know? [7.423494663010787]
  Reasoning language models have set state-of-the-art (SOTA) records on many challenging benchmarks.<n>Like previous language models, reasoning models are prone to generating confident, plausible responses that are incorrect.<n>Knowing when and how much to trust these models is critical to the safe deployment of reasoning models in real-world applications.
  arXiv  Detail & Related papers  (2025-06-22T21:46:42Z)
• SEAL: Steerable Reasoning Calibration of Large Language Models for Free [58.931194824519935]
  Large Language Models (LLMs) have demonstrated compelling capabilities for complex reasoning tasks via the extended chain-of-thought (CoT) reasoning mechanism.<n>Recent studies reveal substantial redundancy in the CoT reasoning traces, which negatively impacts model performance.<n>We introduce SEAL, a training-free approach that seamlessly calibrates the CoT process, improving accuracy while demonstrating significant efficiency gains.
  arXiv  Detail & Related papers  (2025-04-07T02:42:07Z)

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.