The paper addresses the challenge of extracting reliable posterior uncertainty from probabilistic text generators, such as large language models, which provide phrase-level probabilities that are prompt-dependent and incomplete. It formulates the recovery of the target posterior as a semiparametric inverse problem and introduces honest recovery guarantees that jointly consider calibration error, measurement noise, incomplete probabilities, and weak identification. Simulations and studies on frozen language models validate the method’s coverage and stability, showing how to determine when a semantic measurement can be trusted for inference or when recalibration or abstention is needed.
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:2606. 07822v1 Announce Type: cross Abstract: As language models improve and become increasingly deployed to solve a variety of tasks, trustworthiness becomes essential.
arXiv:2603. 25450v2 Announce Type: replace Abstract: Detecting when a language model is wrong without ground truth labels is a fundamental challenge for safe deployment.
arXiv:2607. 19367v1 Announce Type: new Abstract: Calibration is the primary criterion for evaluating LLM confidence, but it is insufficient: it admits trivially incoherent estimators, depends on the evaluation distribution, and does not test the extent to which the estimation can be interpreted as a consistent, underlying probability function.
arXiv:2608. 13591v1 Announce Type: new Abstract: High-confidence errors in large language models are often treated as evidence of fragile internal inference.
arXiv:2604.11662v2 Announce Type: replace Abstract: Recent work has shown that the hidden states of large language models contain signals useful for uncertainty estimation, motivating a growing inter...
arXiv:2609.20973v1 Announce Type: cross Abstract: Complex problem solving (CPS) with large language models (LLMs) is often framed as a matter of stronger reasoning or longer generation. Yet early-ste...
Pinocchio is an external calibrator that provides fast uncertainty estimates for black-box language models. It predicts the correctness of responses from seven trained LLMs with an AUROC of 0.862 and can transfer zero‑shot to thirteen unseen models from eight organizations. The method requires only a single forward pass and no access to the target model’s internal states, and a lightweight 0.8B checkpoint achieves comparable performance.
arXiv:2608. 07827v1 Announce Type: new Abstract: Confidence estimation for large language models (LLMs) aims to estimate the probability that a generated answer is correct, while calibration aligns these estimates with empirical accuracy.
The paper introduces a framework called stochastic lexical calculus that determines when probabilities produced by large language models can be used to represent sequential states in scientific systems. It defines typed measurable transformations of contextual language, constructs a minimal closed representation, and provides necessary and sufficient conditions for unique semantic updates. The authors prove bounds on irreducible nonclosure and accumulated error, and show that under average contraction an external random recursion on a probability simplex is stable and unique. Empirical tests on frozen experiments demonstrate that raw prompt-conditioned probabilities fail an invariance gate, but after prompt-specific calibration a common three-state representation satisfies stability gates and covers 28 of 30 eight-step paths, achieving 0.933 coverage at a nominal 0.90 level.
arXiv:2605. 02122v2 Announce Type: replace-cross Abstract: Human evaluation remains the primary standard for assessing modern AI systems, yet annotator disagreement, bias, and variability make system rankings fragile under standard majority vote aggregation.
arXiv:2607. 03882v1 Announce Type: cross Abstract: LLMs are increasingly deployed as post-hoc explainers of AI-generated outputs, yet it remains unclear whether they can reliably communicate probabilistic information in natural language.