LLM rerankers can internally predict ranking quality via self-consistency of sampled outputs, matching SOTA external QPP while direct confidence is overconfident; supervised token-efficient methods improve calibration.
Do large language models know what they don’t know? arXiv preprint arXiv:2305.18153
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
roles
background 3representative citing papers
LLMs predict outcomes of real scientific experiments at 14-26% accuracy, comparable to human experts, but lack calibration on prediction reliability while humans demonstrate strong calibration.
Introduces Zoom-then-Diagnose paradigm and uncertainty-aware reward in GRPO for confidence-aware ultrasound VQA, reporting 39.3% improvement in lesion localization across liver, breast, and thyroid datasets.
Clarification-seeking in LLM agents amplifies prompt injection attack success from ~2% to over 30% across ten frontier models in a new 728-scenario benchmark.
LLMs show measurable self-recognition that linearly correlates with self-preference bias in evaluations, supported by fine-tuning experiments and controls for confounders.
BaRA adds Bayesian adaptive rank allocation to LoRA fine-tuning by activating sparse instance-specific latent factors, with a generalization bound depending on learned joint effective rank rather than fixed maximum rank.
SingGuard introduces a policy-adaptive multimodal LLM guardrail with dynamic reasoning regimes and SingGuard-Bench, reporting SOTA F1 scores across 35 datasets and improved policy-following accuracy under runtime shifts.
AVA is a specialized GenAI platform for development policy research that provides verifiable syntheses from World Bank reports and is associated with 2.4-3.9 hours of weekly time savings in a large-scale user evaluation.
TrustLLM defines eight trustworthiness principles, creates a six-dimension benchmark, and evaluates 16 LLMs showing proprietary models generally lead but some open-source ones are close while over-calibration can hurt utility.
Proposes Machine Psychometrics and the Machine Mindprint as a measurement science for behavioral and metacognitive traits in artificial agents to support deployment decisions.
citing papers explorer
No citing papers match the current filters.