BICR uses blind-image contrastive ranking on frozen LVLM hidden states to train a lightweight probe that penalizes confidence on blacked-out inputs, yielding top calibration and discrimination across five models and multiple tasks at low parameter cost.
Uncertainty estimation in autoregressive structured prediction
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
verdicts
UNVERDICTED 9representative citing papers
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.
Semantic entropy improves uncertainty estimation in natural language generation by incorporating semantic equivalences, outperforming standard entropy baselines on predicting model accuracy for question answering.
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.
citing papers explorer
-
Grounded or Guessing? LVLM Confidence Estimation via Blind-Image Contrastive Ranking
BICR uses blind-image contrastive ranking on frozen LVLM hidden states to train a lightweight probe that penalizes confidence on blacked-out inputs, yielding top calibration and discrimination across five models and multiple tasks at low parameter cost.
-
Towards Annotation-Free Validation of MLLMs: A Vision-Language Logical Consistency Metric
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.
-
Estimating the Black-box LLM Uncertainty with Distribution-Aligned Adversarial Distillation
DisAAD trains a 1%-sized proxy model via adversarial distillation to quantify uncertainty in black-box LLMs by aligning with their output distributions.
-
Unsupervised Confidence Calibration for Reasoning LLMs from a Single Generation
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-Based Uncertainty Estimation for Code Correctness Estimation
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.
-
Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation
Semantic entropy improves uncertainty estimation in natural language generation by incorporating semantic equivalences, outperforming standard entropy baselines on predicting model accuracy for question answering.
-
Feature Rivalry in Sparse Autoencoder Representations: A Mechanistic Study of Uncertainty-Driven Feature Competition in LLMs
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.
-
Testing the Assumptions of Active Learning for Translation Tasks with Few Samples
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.
-
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.