Ensemble Diversity Optimization jointly learns ensemble weights, size, and a signed diversity regularizer, substantially improving calibration to annotator distributions on subjective text classification.
When the Majority is Wrong: Modeling Annotator Disagreement for Subjective Tasks
4 Pith papers cite this work, alongside 12 external citations. Polarity classification is still indexing.
4
Pith papers citing it
12
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
years
2026 4roles
background 1polarities
background 1representative citing papers
Large-scale statistical analysis of four harmful language datasets reveals that interactions between annotator characteristics and linguistic cues drive annotation variation, with lexical features and attitudes prominent but patterns varying by dataset.
STABLEVAL produces stable AI system rankings by modeling latent correctness and annotator confusion rather than majority vote aggregation.
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
-
Ensemble Diversity Optimization for Subjective Supervision
Ensemble Diversity Optimization jointly learns ensemble weights, size, and a signed diversity regularizer, substantially improving calibration to annotator distributions on subjective text classification.
-
Who and What? Using Linguistic Features and Annotator Characteristics to Analyze Annotation Variation
Large-scale statistical analysis of four harmful language datasets reveals that interactions between annotator characteristics and linguistic cues drive annotation variation, with lexical features and attitudes prominent but patterns varying by dataset.
-
STABLEVAL: Disagreement-Aware and Stable Evaluation of AI Systems
STABLEVAL produces stable AI system rankings by modeling latent correctness and annotator confusion rather than majority vote aggregation.
-
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.