Paul Röttger

A new dataset aims to improve hate speech detection models for the German language.

A review of datasets focused on enhancing LLM safety.

Exploring the responsible use of generative AI technology in various fields.

Examines cultural bias in hate speech datasets and its impact on detection systems.

Study shows larger models don’t guarantee better persuasive messages.

Examining risks of many-shot jailbreaking in Italian language models.

New dataset reveals challenges in detecting hate speech across languages and platforms.