arXiv:2608. 10406v1 Announce Type: cross Abstract: Web search, product search, and question-answering retrieval systems often assign a relevance label and confidence score to each query-candidate pair.
arXiv:2607. 20537v1 Announce Type: cross Abstract: We introduce ReliableTableQA, a framework for training an LLM to annotate the statistical reliability of tabular QA results, not whether the query is answerable, but whether the computed answer is statistically meaningful.
arXiv:2609.13288v1 Announce Type: new Abstract: Video-language models can answer multiple-choice questions with high confidence yet be wrong. We study whether answer-level reliability scores can be i...
The paper investigates how AI systems that perform best‑of‑n search require different validation strategies as the search width changes. It shows that auditing only small search widths leaves a gap in reliability estimates for larger widths, and proposes retaining candidate ranks and truth labels to estimate reliability across all widths up to N. The authors derive theoretical bounds on the minimax mean‑squared error, design procedures that achieve these bounds, and demonstrate that a shared audit can significantly reduce maximum error across many widths in practical CodeRM pools.
The paper introduces Counterfactual Fragility Certificates (CFC), a model‑agnostic audit protocol that maps each prediction to an evidence‑failure trajectory, summarizing it with metrics such as greedy flip budget, margin‑collapse area, degradation thresholds, and fragility dominance score. CFC is shown to identify brittle high‑confidence predictions on seven tabular benchmarks with an AUROC of 0.915, outperforming existing scalar scores by up to +0.405. The method remains effective across various perturbation and review‑budget scenarios, and can also inform fragility‑aware regularization and temperature correction.
arXiv:2608. 09768v1 Announce Type: new Abstract: A prediction that is both confident and wrong is a critical reliability failure because it can bypass abstention and human review precisely when the model is mistaken.
arXiv:2606. 03650v1 Announce Type: cross Abstract: Choosing or ranking language models for a specific application is hardest when no task-specific labeled data exists, and standard public benchmarks cannot be trusted, their items having likely leaked into pretraining, so scores reflect memorization rather than fitness.
arXiv:2609.10333v1 Announce Type: new Abstract: Uncertainty estimation for medical vision--language models (VLMs) using conformal prediction has gained increasing attention due to its distribution-fr...
arXiv:2609.36900v1 Announce Type: new Abstract: Reward hacking occurs when policy optimization exploits a brittle reward interface or an overly permissive proxy objective, improving the training scor...
arXiv:2604.08974v2 Announce Type: replace Abstract: Uncertainty quantification techniques measure confidence in language model outputs to support critical applications like hallucination detection an...
arXiv:2609.26468v1 Announce Type: new Abstract: A key factor in deciding whether to trust an automatic prediction is its confidence score, which should be calibrated to match the actual probability o...
Safety-Flag is a unified benchmark that consolidates seven popular safety datasets into a single balanced flag/do‑not‑flag protocol, providing item‑level decisions and confidence scores for multiple large language models and dedicated guards. The benchmark evaluates moderator reliability across three dimensions—error direction, probability calibration, and confidence‑based error ranking—revealing that aggregate accuracy masks significant differences, such as one model flagging 85% of benign content while another misses 54% of harmful content. The study shows that general‑purpose models are overconfident, but temperature tuning can substantially improve calibration, and confidence‑based abstention can reduce selective risk, though performance varies with how well confidence ranks errors.
arXiv:2608. 02455v1 Announce Type: new Abstract: Human-centered assessment tasks, which are essential for systematic decision-making, rely heavily on human judgment and typically lack verifiable ground truth.