arXiv AI
Aug 10
Same Answer, Different Confidence: Protocol Sensitivity in LLM Confidence Calibration
arXiv:2605. 27752v3 Announce Type: replace Abstract: Is verbalized confidence better calibrated than token likelihood?
Asking Is Not Enough: Protocol Sensitivity in LLM Confidence Calibration
arXiv:2605. 27752v2 Announce Type: replace Abstract: LLM confidence calibration is often evaluated by comparing two signals: token-probability scores and verbalized confidence.
Related stories
arXiv AI
Sep 21
How do LLMs Compute Verbal Confidence
arXiv:2603.17839v4 Announce Type: replace-cross Abstract: Verbal confidence -- prompting LLMs to state their confidence as a number or category -- is widely used to extract uncertainty estimates from...
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 Machine Learning
Jun 10
Calibrating Overconfidence Without Sacrificing Confidence: Probe-Conditioned Head Intervention for LLMs
arXiv:2606. 09876v1 Announce Type: new Abstract: Large language models often express high confidence in answers that are wrong.
arXiv AI
Aug 11
When Confidence Fails: Overconfidence in LLMs under Uncertainty and Missing Clinical Information
arXiv:2608. 09080v1 Announce Type: cross Abstract: Large Language Models (LLMs) have achieved strong performance in medical question answering and clinical reasoning tasks.
arXiv Computation and Language
Sep 18
An Analysis of Training-Free Self-Reported Confidence in Language Models
The paper investigates whether language models’ self-reported confidence is meaningful without additional training. By evaluating three training‑free signals—direct verbalization, post‑hoc probability estimates, and agreement across multiple generations—on 100 TriviaQA questions, the authors find that direct verbalization alone achieves high AUROC scores (0.956 and 0.937) for correctness prediction, while agreement-based methods perform noticeably worse. Re‑eliciting confidence for the same answers shows modest score shifts and occasional decision flips, and an audit of biography claims reveals only a small confidence gap between supported and contradicted statements.
arXiv Computation and Language
Sep 23
Truth for Believable AI: Expressed Doubt, Provenance, and Belief Revision as an Engineerable Stance
arXiv:2609.26035v1 Announce Type: new Abstract: Conversational agents often express answers in a uniformly confident register. We test whether expressed uncertainty, provenance-aware assertion, and e...
arXiv AI
Aug 6
Provable Limits and Certified Deferral for Verbalized Uncertainty in Small Language Models
arXiv:2608. 05064v1 Announce Type: cross Abstract: Small open-weight language models increasingly run in private, offline, and cost-sensitive settings, where the key deployment question is not only what a model answers but when it should defer to a human.
arXiv AI
Jun 24
CALIBER: Calibrating Confidence Before and After Reasoning in Language Models
arXiv:2606. 24281v1 Announce Type: cross Abstract: Reasoning language models are increasingly asked not only to answer difficult questions, but also to estimate their likelihood of success.
arXiv AI
Sep 17
Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents
The paper introduces XConf, an experiential confidence estimator that augments a language model’s current inference with a record of its past graded episodes. By recalling similar past tasks and reflecting on past outcomes, XConf generates confidence scores without accessing logits or updating weights, achieving superior discrimination and calibration across diverse benchmarks. The method demonstrates significant gains in selective prediction, improving success rates on agent tasks by up to 8.7 points.
arXiv Computation and Language
Sep 11
Rethinking Verbalized Confidence for LLM-as-a-Judge: A Compatibility Shift on Post-2025 Proprietary Models
The paper argues that verbalized confidence—once viewed as overconfident and coarse—has become the preferred soft‑scoring method for LLM‑as‑a‑Judge on top‑tier proprietary models released after 2025. Experiments on SummEval, AggreFact, and HelpSteer2 across up to 18 LLMs show that log‑probabilities are no longer the best signal, and that adding an overconfidence advisory and self‑debate further improves calibration and robustness. The authors note that these enhancements incur little accuracy loss on post‑2025 models but do affect pre‑2025 ones, highlighting a compatibility shift in how confidence should be measured.
arXiv AI
Jun 9
The ACUTE Protocol: Operationalizing Language Model Activations for Better Calibration, Utility, and Trust
arXiv:2606. 07822v1 Announce Type: cross Abstract: As language models improve and become increasingly deployed to solve a variety of tasks, trustworthiness becomes essential.