About

Oskar van der Wal

Oskar van der Wal

PhD Student

Oskar van der Wal is a PhD candidate at the Institute for Logic, Language and Computation (ILLC) at the University of Amsterdam, under the guidance of Katrin Schulz and Jelle Zuidema.

His research focuses on understanding the origins and manifestations of social biases in language models. To that end he, for example, works on the project “Improving Language Model bias measures” to ensure that methods for measuring bias in Natural Language Processing (NLP) technology are reliable.

Language models White
Bias White

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
Language models White
Bias White
Theory-driven White
Ongoing

Papers by the researcher

Can NLP bias measures be trusted?

Browse blogs written by the researcher

Discover our researchers’ blogs—icons by each post indicate its themes.

Language models White
Bias White

Going beyond a mathematical investigation of bias