A per-token feature from temperature-induced changes in LLM token distributions predicts within-prompt creativity rank at Spearman rho 0.918 vs LLM judges and 0.870 vs humans, outperforming perplexity, entropy, top-1 margin, and compression baselines.
hub
Uncertainty estimation in autoregressive structured prediction
18 Pith papers cite this work. Polarity classification is still indexing.
18
Pith papers citing it
hub tools
citation-role summary
background 1
method 1
citation-polarity summary
verdicts
UNVERDICTED 18representative citing papers
A between-subjects experiment (N=192) finds that token-level uncertainty increases agreement with LLM answers while relation-level uncertainty reduces external verification in medical decision tasks.
BICR trains a lightweight probe on contrastive hidden states from real versus blind images to detect visual grounding in LVLM predictions, outperforming baselines on calibration and discrimination with fewer parameters.
Token entropy distributions fingerprint hallucinations in generative models, enabling the Calibrated Entropy Score (CES) for single-pass black-box detection with calibration guarantees via a novel DKW inequality.
BalanceRAG uses sequential graphical testing on a 2D lattice of threshold pairs to certify safe operating points that meet target risk levels in cascaded RAG while increasing coverage.
VL-LCM measures vision-language logical consistency without annotations and shows that recent MLLMs have high accuracy but low logical consistency on benchmarks like MMMU and NaturalBench.
DisAAD trains a 1%-sized proxy model via adversarial distillation to quantify uncertainty in black-box LLMs by aligning with their output distributions.
Unsupervised single-generation confidence calibration for reasoning LLMs via offline self-consistency proxy distillation outperforms baselines on math and QA tasks and improves selective prediction.
Ensemble Semantic Entropy improves correlation with code correctness over single-model methods and powers a cascading scaling system that cuts FLOPs by 64.9% while preserving performance on LiveCodeBench.
GlimpRouter uses the entropy of the first token in each reasoning step to decide whether to invoke a large model, yielding 10.7% higher accuracy and 25.9% lower latency than a standalone large model on AIME25.
Entropy After </Think> (EAT) enables early exiting in reasoning LLMs by tracking entropy stabilization after a </think> token, cutting token use 12-22% on MATH500 and AIME2025 with no accuracy loss.
LLMs achieve higher accuracy than humans on compositional imagery tasks previously argued to require pictorial representations, supporting emergent propositional mental imagery in AI.
Semantic entropy improves uncertainty estimation in natural language generation by incorporating semantic equivalences, outperforming standard entropy baselines on predicting model accuracy for question answering.
Mainstream UQ for LLMs reduces to unsupervised clustering of internal generation consistency and therefore cannot detect confident hallucinations or provide reliable safety signals.
Feature rivalry in SAE representations strengthens with model uncertainty on high-entropy questions, enables output steering, and predicts answer correctness with AUROC 0.689 in Gemma-2-2B.
Informativeness and diversity of samples selected by active learning show no correlation with test performance on translation tasks using few samples; ordering and pre-training effects dominate instead.
Supervised fine-tuning degrades the correlation between confidence scores and output quality in language models, driven by factors like training distribution similarity rather than true quality.
Introduces Explicit Logic Channel (ELC) with LLM, VFM and probabilistic inference for validating, selecting and enhancing MLLMs on zero-shot tasks using Consistency Rate and cross-channel integration.
citing papers explorer
-
Confident in a Confidence Score: Investigating the Sensitivity of Confidence Scores to Supervised Fine-Tuning
Supervised fine-tuning degrades the correlation between confidence scores and output quality in language models, driven by factors like training distribution similarity rather than true quality.