Face-Feature Tuning is a label-free logit remapping method that reduces FPR/TPR gaps across groups in deepfake detection while preserving overall accuracy.
hub
Bias in Computer Systems
4 Pith papers cite this work, alongside 1,104 external citations. Polarity classification is still indexing.
4
Pith papers citing it
1,104
external citations · external index
hub tools
representative citing papers
H-SAL erases latent concepts from text profiles using self-descriptions as implicit debiasing signals and shows competitive performance on a new multi-domain Stack Exchange helpfulness benchmark.
The authors conduct a systematic literature review and real-world analysis to define Crowdsourced Context Systems and map a six-aspect design space with normative implications.
Experts rate AI scenarios as more likely, less risky, more beneficial, and more valuable than the public, applying different weightings to risk versus benefit.
citing papers explorer
-
Toward Calibrated, Fair, and accurate Deepfake Detection
Face-Feature Tuning is a label-free logit remapping method that reduces FPR/TPR gaps across groups in deepfake detection while preserving overall accuracy.
-
Debiasing Without Protected Attributes: Latent Concept Erasure from Textual Profiles
H-SAL erases latent concepts from text profiles using self-descriptions as implicit debiasing signals and shows competitive performance on a new multi-domain Stack Exchange helpfulness benchmark.
-
Beyond Community Notes: A Framework for Understanding and Building Crowdsourced Context Systems for Social Media
The authors conduct a systematic literature review and real-world analysis to define Crowdsourced Context Systems and map a six-aspect design space with normative implications.
-
Perception Gaps in Risk, Benefit, and Value Between Experts and Public Challenge Socially Accepted AI
Experts rate AI scenarios as more likely, less risky, more beneficial, and more valuable than the public, applying different weightings to risk versus benefit.