arXiv:2606. 29490v1 Announce Type: cross Abstract: Confidence is an estimate of the probability that a chosen answer is correct.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
Reliable confidence -- the probability that a model's own answer is correct -- is essential for the trustworthy deployment of language models. Existing work has largely evaluated confidence by how well it predicts correctness and whether it is calibrated, leaving open a more fundamental question: what does the confidence signal itself represent?
arXiv:2607. 12447v1 Announce Type: cross Abstract: Reliable confidence -- the probability that a model's own answer is correct -- is essential for the trustworthy deployment of language models.
arXiv:2607. 16451v1 Announce Type: cross Abstract: Chat models sometimes commit to an answer and then produce reasoning that justifies it rather than deriving it -- even when the answer contradicts a task premise.
arXiv:2605. 27752v2 Announce Type: replace Abstract: LLM confidence calibration is often evaluated by comparing two signals: token-probability scores and verbalized confidence.
arXiv:2608. 09080v1 Announce Type: cross Abstract: Large Language Models (LLMs) have achieved strong performance in medical question answering and clinical reasoning tasks.
arXiv:2606. 25013v1 Announce Type: new Abstract: Today's reasoning models use thinking tokens to attain stronger performance on benchmarks than their instruction-tuned counterparts.