Dirk Hovy

Examining the effectiveness of language models for classifying human language data.

A new test suite evaluates safety behaviors in language models.

A study on combining group and individual traits in natural language processing.

A new method simplifies understanding of speech classification models.

Research challenges traditional methods of evaluating language model values and opinions.

Examining performance gaps in speech recognition across different genders.

This article examines gender biases in language models and their implications.

A review of datasets focused on enhancing LLM safety.

New metrics improve large language models' effectiveness in education.

Explores how language models portray emotions linked to diverse religions.

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

Exploring new methods for effective social media content moderation.