The Knowing-Saying Gap: When Probes See Errors that Confidence Misses

• URL: http://arxiv.org/abs/2608.07528v1
• Date: Tue, 21 Jul 2026 12:13:10 GMT
• Title: The Knowing-Saying Gap: When Probes See Errors that Confidence Misses
• Abstract summary: Linear probes detect corrupted context in language models with near-perfect accuracy, yet this does not translate into reliable failure prediction.<n>Across multi-hop arithmetic chains, probes that detect corruption turn out to be uninformative about final answer correctness.<n>As a real-time monitor, probe-based interventions are sharply model and error-type dependent.
• Score: 20.46211358172975
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Linear probes detect corrupted context in language models with near-perfect accuracy, yet this does not translate into reliable failure prediction. The result is a dissociation with direct implications for deployment monitoring. Across multi-hop arithmetic chains, probes that detect corruption turn out to be uninformative about final answer correctness; models forced into structured confidence formats collapse to two values with indistinguishable error rates; and probe persistence across hops fails to separate correct from incorrect outcomes, refuting our pre-registered "persistence beats peak" hypothesis. This pattern of knowing but not saying generalises across model families including reasoning models. As a real-time monitor, probe-based interventions are sharply model and error-type dependent: branch-and-pick is net-positive across models and uniquely non-breaking on Llama-3.1-8B (4 rescued, 0 broken), while reprompt and replace-prior break correct traces at roughly the rate they rescue wrong ones. Probe-based monitoring is a necessary complement to verbalised confidence, but no single intervention dominates, and the deployable answer is model-aware, error-type-aware routing.

Related papers

• DirEAG: Dirichlet Evidence Aggregation for Calibrating Verbalized Confidence in Mathematical Reasoning [2.867517731896504]
  Black-box verbalized confidence is difficult to calibrate in large language models.<n>We propose DirEAG, a Dirichlet Evidence Aggregation method that converts each elicited answer-confidence observation into calibrated soft evidence.
  arXiv  Detail & Related papers  (2026-08-21T03:48:25Z)
• Sensitivity Uncertainty Alignment in Large Language Models [0.0]
  We propose a framework for analyzing failures of large language models under adversarial and ambiguous inputs.<n>We define a scalar score, SUA_theta(x), capturing the difference between distributional sensitivity and predictive entropy.<n>We introduce SUA-TR, a training method combining consistency regularization and entropy alignment, along with an abstention rule for safer inference.
  arXiv  Detail & Related papers  (2026-04-21T17:53:12Z)
• Closing the Confidence-Faithfulness Gap in Large Language Models [3.122242683664973]
  Large language models verbalize confidence scores that are largely detached from their actual accuracy.<n>We present a mechanistic interpretability analysis of verbalized confidence.<n>We introduce a two-stage adaptive steering pipeline that reads the model's internal accuracy estimate and steers verbalized output to match it.
  arXiv  Detail & Related papers  (2026-03-26T05:42:04Z)
• Silent Commitment Failure in Instruction-Tuned Language Models: Evidence of Governability Divergence Across Architectures [0.0]
  We introduce governability -- the degree to which a model's errors are detectable before output commitment and correctable once detected.<n>We show benchmark accuracy does not predict governability, correction capacity varies independently of detection, and identical governance scaffolds produce opposite effects across models.<n>We propose a Detection and Correction Matrix classifying model-task combinations into four regimes: Governable, Monitor Only, Steer Blind, and Ungovernable.
  arXiv  Detail & Related papers  (2026-03-22T21:50:28Z)
• Revisiting Multivariate Time Series Forecasting with Missing Values [65.30332997607141]
  Missing values are common in real-world time series.<n>Current approaches have developed an imputation-then-prediction framework that uses imputation modules to fill in missing values, followed by forecasting on the imputed data.<n>This framework overlooks a critical issue: there is no ground truth for the missing values, making the imputation process susceptible to errors that can degrade prediction accuracy.<n>We introduce Consistency-Regularized Information Bottleneck (CRIB), a novel framework built on the Information Bottleneck principle.
  arXiv  Detail & Related papers  (2025-09-27T20:57:48Z)
• Probing for Arithmetic Errors in Language Models [86.8227317662622]
  Internal activations in language models can be used to detect arithmetic errors.<n>We show that simple probes can accurately decode both the model's predicted output and the correct answer from hidden states.<n>We train lightweight error detectors that predict model correctness with over 90% accuracy.
  arXiv  Detail & Related papers  (2025-07-16T16:27:50Z)
• Selective Learning: Towards Robust Calibration with Dynamic Regularization [79.92633587914659]
  Miscalibration in deep learning refers to there is a discrepancy between the predicted confidence and performance. We introduce Dynamic Regularization (DReg) which aims to learn what should be learned during training thereby circumventing the confidence adjusting trade-off.
  arXiv  Detail & Related papers  (2024-02-13T11:25:20Z)
• 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)
• TRUST-LAPSE: An Explainable and Actionable Mistrust Scoring Framework for Model Monitoring [4.262769931159288]
  We propose TRUST-LAPSE, a "mistrust" scoring framework for continuous model monitoring. We assess the trustworthiness of each input sample's model prediction using a sequence of latent-space embeddings. Our latent-space mistrust scores achieve state-of-the-art results with AUROCs of 84.1 (vision), 73.9 (audio), and 77.1 (clinical EEGs)
  arXiv  Detail & Related papers  (2022-07-22T18:32:38Z)
• Training on Test Data with Bayesian Adaptation for Covariate Shift [96.3250517412545]
  Deep neural networks often make inaccurate predictions with unreliable uncertainty estimates. We derive a Bayesian model that provides for a well-defined relationship between unlabeled inputs under distributional shift and model parameters. We show that our method improves both accuracy and uncertainty estimation.
  arXiv  Detail & Related papers  (2021-09-27T01:09:08Z)
• Improving Uncertainty Calibration via Prior Augmented Data [56.88185136509654]
  Neural networks have proven successful at learning from complex data distributions by acting as universal function approximators. They are often overconfident in their predictions, which leads to inaccurate and miscalibrated probabilistic predictions. We propose a solution by seeking out regions of feature space where the model is unjustifiably overconfident, and conditionally raising the entropy of those predictions towards that of the prior distribution of the labels.
  arXiv  Detail & Related papers  (2021-02-22T07:02:37Z)

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.