Harmful Speech Detection by Language Models Exhibits Gender Queer Dialect Bias

About this video

Advanced · Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video · 82% confidence

Documents gender and dialect bias in harmful-speech detection by language models. Empirical study of fairness failures in NLP systems.

A 19-minute video from Association for Computing Machinery (ACM): “Harmful Speech Detection by Language Models Exhibits Gender Queer Dialect Bias”.

Video by Association for Computing Machinery (ACM), played through YouTube's embedded player.

Part of ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO'24)