When in Doubt, Consult: Expert Debate for Sexism Detection via Confidence-Based Routing
Anwar Alajmi, Gabriele Pergola

TL;DR
This paper introduces a two-stage framework for detecting subtle online sexism, combining stabilized training with a dynamic expert routing mechanism to improve accuracy on ambiguous cases.
Contribution
It proposes a novel two-stage approach with targeted regularization and a reasoning-based expert system for better sexism detection in complex, noisy datasets.
Findings
Outperforms existing methods on public benchmarks.
Achieves significant F1 score improvements (+4.48%, +1.30%).
Enhances detection of subtle, context-dependent sexism.
Abstract
Online sexism increasingly appears in subtle, context-dependent forms that evade traditional detection methods. Its interpretation often depends on overlapping linguistic, psychological, legal, and cultural dimensions, which produce mixed and sometimes contradictory signals in annotated datasets. These inconsistencies, combined with label scarcity and class imbalance, result in unstable decision boundaries and cause fine-tuned models to overlook subtler, underrepresented forms of harm. To address these challenges, we propose a two-stage framework that unifies (i) targeted training procedures to better regularize supervision to scarce and noisy data with (ii) selective, reasoning-based inference to handle ambiguous or borderline cases. First, we stabilize the training combining class-balanced focal loss, class-aware batching, and post-hoc threshold calibration, strategies for the firs…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMultimodal Machine Learning Applications · Topic Modeling · Domain Adaptation and Few-Shot Learning
