Controlled experiments on MNIST show human soft-labels act as a regularizer that improves calibration on hard samples and aligns model uncertainty with humans, beyond accuracy gains from correcting mislabels.
Stop measuring calibration when humans disagree
5 Pith papers cite this work, alongside 21 external citations. Polarity classification is still indexing.
5
Pith papers citing it
21
external citations · OpenAlex
citation-role summary
background 2
method 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5representative citing papers
VLMs fail to identify visual preconditions or apply physical laws in kinematic physics tasks, as shown by new FACT diagnostics and NICE calibration methods evaluated on six state-of-the-art models.
Annotation disagreement on toxic language can be moderately predicted from textual features, with high-opposition items proving harder for models to estimate accurately.
Socio-Contrastive Learning jointly learns socio-demographic representations and textual features via contrastive objectives to predict annotator perspectives more accurately than concatenation baselines.
Automated hate speech detectors show poor alignment with heterogeneous in-group judgments on reclaimed slur usage, driven by low inter-annotator agreement and contextual features like derogatory intent.
citing papers explorer
-
An Assessment of Human vs. Model Uncertainty in Soft-Label Learning and Calibration
Controlled experiments on MNIST show human soft-labels act as a regularizer that improves calibration on hard samples and aligns model uncertainty with humans, beyond accuracy gains from correcting mislabels.
-
NICE FACT: Diagnosing and Calibrating VLMs in Quantitative Reasoning for Kinematic Physics
VLMs fail to identify visual preconditions or apply physical laws in kinematic physics tasks, as shown by new FACT diagnostics and NICE calibration methods evaluated on six state-of-the-art models.
-
Quantifying and Predicting Disagreement in Graded Human Ratings
Annotation disagreement on toxic language can be moderately predicted from textual features, with high-opposition items proving harder for models to estimate accurately.
-
Modeling Human Perspectives with Socio-Demographic Representations
Socio-Contrastive Learning jointly learns socio-demographic representations and textual features via contrastive objectives to predict annotator perspectives more accurately than concatenation baselines.
-
IYKYK (But AI Doesn't): Automated Content Moderation Does Not Capture Communities' Heterogeneous Attitudes Towards Reclaimed Language
Automated hate speech detectors show poor alignment with heterogeneous in-group judgments on reclaimed slur usage, driven by low inter-annotator agreement and contextual features like derogatory intent.