#ai-auditing2 articles

2 articles

AINeutralarXiv – CS AI · 5h ago

🧠

ACES: Accent Subspaces for Coupling, Explanations, and Stress-Testing in Automatic Speech Recognition

Researchers introduce ACES, a new method to analyze how automatic speech recognition systems perform differently across accents. The study finds that accent information is concentrated in early neural network layers and is deeply intertwined with speech recognition capabilities, making simple bias removal ineffective.

AINeutralarXiv – CS AI · 5h ago

🧠

On the Suitability of LLM-Driven Agents for Dark Pattern Audits

Researchers evaluated LLM-driven agents' ability to identify dark patterns in web interfaces, specifically testing on 456 data broker websites processing CCPA data rights requests. The study examined whether AI agents can reliably detect manipulative design elements that discourage users from exercising their privacy rights.