arXiv Computation and Language
An Analysis of Training-Free Self-Reported Confidence in Language Models
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv AI
Jul 24
ConfidenceBench: Evaluating Confidence Calibration in Large Language Models
arXiv:2607. 20526v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in settings where fluent but incorrect answers can be costly.
arXiv Computation and Language
Aug 31
When Linguistic and Internal Confidence Diverge in Large Language Models
arXiv:2608.28382v1 Announce Type: new Abstract: Users often ask large language models (LLMs) to report how confident they are, but it is unclear whether such linguistic confidence tracks the model's...
arXiv Computation and Language
Aug 25
Claim-Level Confidence Calibration for Reliable Decision Making with Large Language Models
arXiv:2608.22483v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly support decision-making in high-stakes domains, but they often hallucinate and express confidence that is mis...
arXiv AI
Jul 9
Future Confidence Distillation in Large Language Models
arXiv:2607. 07626v1 Announce Type: cross Abstract: Reliable confidence estimation is essential for deploying large language models (LLMs) in confidence-aware systems, where downstream decisions such as retrieval, tool use, and adaptive computation depend on accurately estimating answer reliability.
arXiv AI
Aug 17
Stable Miscalibration in Large Language Models: A Practical View of High-Confidence Errors
arXiv:2608. 13591v1 Announce Type: new Abstract: High-confidence errors in large language models are often treated as evidence of fragile internal inference.
arXiv AI
2d ago
The Mirage of Calibrated Confidence: Trajectory-Independence of Verbalized Confidence in Vision-Language Models
The paper investigates how Vision‑Language Models (VLMs) often report high confidence even after self‑correcting or arriving at wrong answers, a phenomenon the authors attribute to the verbalized confidence being largely independent of the model’s reasoning trajectory. By analyzing content variation, token masking, and hesitation markers, the authors demonstrate that confidence does not adequately reflect the actual reasoning process and that calibration training can sometimes worsen this disconnect. To address this blind spot, they introduce the Trajectory‑Grounding Score (TGS) in two forms—TGS‑self and TGS‑pair—and propose TGS‑Bench, a suite of 10 benchmarks that reveal divergences between conventional calibration metrics and trajectory‑grounded confidence.