About

Alina Leidinger

PhD Student

Alina Leidinger is a PhD candidate at the Institute for Logic, Language and Computation (ILLC) at the University of Amsterdam, supervised by Katia Shutova and Robert van Rooij.

Her research focuses on implicit bias and stereotypes in large Language Models. Alina is part of the project From Learning to Meaning: A new approach to Generic Sentences and Implicit Biases. Previously, she obtained a MSc in Mathematics in Data Science from Technical University of Munich and a BSc in Mathematics from Imperial College London.

Research projects of the researcher

Below you can find a sample of the CERTAIN-related research projects of this researcher.

Improving Language Model Bias Measures

Many researchers develop tools for measuring how biased language models are; in this project we work on improving these tools

Ongoing

From Learning to Meaning

In this project we explore whether Language Model’s generic sentences can teach us something about how people express stereotypes.

Ongoing

Papers by the researcher

How Are LLMs Mitigating Stereotyping Harms? Learning from Search Engine Studies

CIVICS: Building a Dataset for Examining Culturally-Informed Values in Large Language Models

Are LLMs classical or nonmonotonic reasoners? Lessons from generics

How robust and reliable can we expect language models to be?

Which stereotypes do search engines come with?

Can NLP bias measures be trusted?