2 papers
cs.CL2025
FHSTP@EXIST 2025 Benchmark: Sexism Detection with Transparent Speech Concept Bottleneck Models
Roberto Labadie-Tamayo, Adrian Jaques Böck, Djordje Slijepčević +3
Sexism has become widespread on social media and in online conversation. To help address this issue, the fifth Sexism Identification in Social Networks (EXIST) challenge is initiat…
cs.LG2024
Exploring the Plausibility of Hate and Counter Speech Detectors with Explainable AI
Adrian Jaques Böck, Djordje Slijepčević, Matthias Zeppelzauer
In this paper we investigate the explainability of transformer models and their plausibility for hate speech and counter speech detection. We compare representatives of four differ…