BiasLab: Toward Explainable Political Bias Detection with Dual-Axis Annotations and Rationale Indicators

Published in Presented at ICML MoFA, 2025

Recommended citation: Solaiman, KMA (2025). BiasLab: Toward explainable political bias detection with dual-axis annotations and rationale indicators. Presented at 2nd Workshop on Models of Human Feedback for AI Alignment (MoFA) at ICML 2025. https://arxiv.org/abs/2505.16081

Direct Link