From Entropy to Calibrated Uncertainty: Training Language Models to Reason About Uncertainty

• URL: http://arxiv.org/abs/2603.06317v1
• Date: Fri, 06 Mar 2026 14:21:42 GMT
• Title: From Entropy to Calibrated Uncertainty: Training Language Models to Reason About Uncertainty
• Abstract summary: Large Language Models (LLMs) that can express interpretable and calibrated uncertainty are crucial in high-stakes domains.<n>We propose a three-stage pipeline to post-train LLMs to efficiently infer calibrated uncertainty estimates for their responses.<n> Experiments show that models trained with our pipeline achieve better calibration than baselines and generalize to unseen tasks without further processing.
• Score: 9.798854302346802
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) that can express interpretable and calibrated uncertainty are crucial in high-stakes domains. While methods to compute uncertainty post-hoc exist, they are often sampling-based and therefore computationally expensive or lack calibration. We propose a three-stage pipeline to post-train LLMs to efficiently infer calibrated uncertainty estimates for their responses. First, we compute fine-grained entropy-based uncertainty scores on the training data, capturing the distributional variability of model outputs in embedding space. Second, these scores are calibrated via Platt scaling, producing reliable and human-interpretable uncertainty signals. Finally, the target LLM is post-trained via reinforcement learning to align its policy with these calibrated signals through a verifiable reward function. Unlike post-hoc uncertainty estimation methods, our approach provides interpretable and computationally efficient uncertainty estimates at test time. Experiments show that models trained with our pipeline achieve better calibration than baselines and generalize to unseen tasks without further processing, suggesting that they learn a robust uncertainty reasoning behavior.

Related papers

• Unsupervised Confidence Calibration for Reasoning LLMs from a Single Generation [2.526814143603023]
  Reasoning language models can solve increasingly complex tasks, but struggle to produce the calibrated confidence estimates necessary for reliable deployment.<n>We introduce a method for unsupervised confidence calibration of reasoning LLMs when only a single generation is available at inference time.<n>Our approach uses offline sampling on unlabeled data to derive a self-consistency-based proxy target, then distills this signal into a lightweight deployment-time confidence predictor.
  arXiv  Detail & Related papers  (2026-04-21T13:25:25Z)
• 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)
• Calibrating LLM Judges: Linear Probes for Fast and Reliable Uncertainty Estimation [25.80946316489521]
  We introduce linear probes trained with a Brier score-based loss to provide calibrated uncertainty estimates from reasoning judges' hidden states.<n>We evaluate our approach on both objective tasks (reasoning, mathematics, factuality, coding) and subjective human preference judgments.
  arXiv  Detail & Related papers  (2025-12-23T22:08:46Z)
• Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Models [104.55763564037831]
  We train a regression model that leverages attention maps, probabilities on the current generation step, and recurrently computed uncertainty scores from previously generated tokens.<n>Our evaluation shows that the proposed method is highly effective for selective generation, achieving substantial improvements over rivaling unsupervised and supervised approaches.
  arXiv  Detail & Related papers  (2024-08-20T09:42:26Z)
• Error-Driven Uncertainty Aware Training [7.702016079410588]
  Error-Driven Uncertainty Aware Training aims to enhance the ability of neural classifiers to estimate their uncertainty correctly. The EUAT approach operates during the model's training phase by selectively employing two loss functions depending on whether the training examples are correctly or incorrectly predicted. We evaluate EUAT using diverse neural models and datasets in the image recognition domains considering both non-adversarial and adversarial settings.
  arXiv  Detail & Related papers  (2024-05-02T11:48:14Z)
• Calibrated Uncertainty Quantification for Operator Learning via Conformal Prediction [95.75771195913046]
  We propose a risk-controlling quantile neural operator, a distribution-free, finite-sample functional calibration conformal prediction method. We provide a theoretical calibration guarantee on the coverage rate, defined as the expected percentage of points on the function domain. Empirical results on a 2D Darcy flow and a 3D car surface pressure prediction task validate our theoretical results.
  arXiv  Detail & Related papers  (2024-02-02T23:43:28Z)
• Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling [69.83976050879318]
  In large language models (LLMs), identifying sources of uncertainty is an important step toward improving reliability, trustworthiness, and interpretability. In this paper, we introduce an uncertainty decomposition framework for LLMs, called input clarification ensembling. Our approach generates a set of clarifications for the input, feeds them into an LLM, and ensembles the corresponding predictions.
  arXiv  Detail & Related papers  (2023-11-15T05:58:35Z)
• Post-hoc Uncertainty Learning using a Dirichlet Meta-Model [28.522673618527417]
  We propose a novel Bayesian meta-model to augment pre-trained models with better uncertainty quantification abilities. Our proposed method requires no additional training data and is flexible enough to quantify different uncertainties. We demonstrate our proposed meta-model approach's flexibility and superior empirical performance on these applications.
  arXiv  Detail & Related papers  (2022-12-14T17:34:11Z)
• A Close Look into the Calibration of Pre-trained Language Models [56.998539510508515]
  Pre-trained language models (PLMs) may fail in giving reliable estimates of their predictive uncertainty. We study the dynamic change in PLMs' calibration performance in training. We extend two recently proposed learnable methods that directly collect data to train models to have reasonable confidence estimations.
  arXiv  Detail & Related papers  (2022-10-31T21:31:07Z)
• Reliability-Aware Prediction via Uncertainty Learning for Person Image Retrieval [51.83967175585896]
  UAL aims at providing reliability-aware predictions by considering data uncertainty and model uncertainty simultaneously. Data uncertainty captures the noise" inherent in the sample, while model uncertainty depicts the model's confidence in the sample's prediction.
  arXiv  Detail & Related papers  (2022-10-24T17:53:20Z)
• Improving model calibration with accuracy versus uncertainty optimization [17.056768055368384]
  A well-calibrated model should be accurate when it is certain about its prediction and indicate high uncertainty when it is likely to be inaccurate. We propose an optimization method that leverages the relationship between accuracy and uncertainty as an anchor for uncertainty calibration. We demonstrate our approach with mean-field variational inference and compare with state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-12-14T20:19:21Z)

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.