LLMs struggle to associate epistemic markers with stable internal confidence levels across distributions, even under model-centric interpretations, while maintaining somewhat consistent marker rankings.
Aviv Slobodkin, Omer Goldman, Avi Caciularu, Ido Dagan, and Shauli Ravfogel
5 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
5
Pith papers citing it
1
external citations · external index
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
Inducing artificial uncertainty on trivial tasks allows training probes that achieve higher calibration on hard data than standard approaches while retaining performance on easy data.
A new structured prompting method (SPEC) helps AI detect insufficient evidence in adjudication tasks and defer decisions appropriately, reaching 89% accuracy on a benchmark varying information completeness from Colorado unemployment insurance cases.
RLMF uses quality of model self-judgments to refine RL rankings and select training data, achieving SOTA faithful calibration while preserving accuracy and outperforming standard RL by up to 63%.
Empirical study finds overconfidence persists in medical VLMs despite scaling and prompting; post-hoc calibration reduces error while hallucination-aware calibration improves both calibration and AUROC.
citing papers explorer
-
Can LLMs Use Linguistic Uncertainty Markers to Reliably Reflect Intrinsic Confidence?
LLMs struggle to associate epistemic markers with stable internal confidence levels across distributions, even under model-centric interpretations, while maintaining somewhat consistent marker rankings.
-
Inducing Artificial Uncertainty in Language Models
Inducing artificial uncertainty on trivial tasks allows training probes that achieve higher calibration on hard data than standard approaches while retaining performance on easy data.
-
Learning When Not to Decide: A Framework for Overcoming Factual Presumptuousness in AI Adjudication
A new structured prompting method (SPEC) helps AI detect insufficient evidence in adjudication tasks and defer decisions appropriately, reaching 89% accuracy on a benchmark varying information completeness from Colorado unemployment insurance cases.
-
Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs
RLMF uses quality of model self-judgments to refine RL rankings and select training data, achieving SOTA faithful calibration while preserving accuracy and outperforming standard RL by up to 63%.
-
Overconfidence and Calibration in Medical VQA: Empirical Findings and Hallucination-Aware Mitigation
Empirical study finds overconfidence persists in medical VLMs despite scaling and prompting; post-hoc calibration reduces error while hallucination-aware calibration improves both calibration and AUROC.