Try the demo

Find relevant
research papers

Filter: research theme
Filter: researchers
How Are LLMs Mitigating Stereotyping Harms? Learning from Search Engine Studies
  • Leidinger & Rogers
  • Published in 2024
Trustworthy Plum
Responsible Plum
Language models Plum
Fairness Plum
Bias Plum
CIVICS: Building a Dataset for Examining Culturally-Informed Values in Large Language Models
  • Pistilli et al.
  • Published in 2024
Trustworthy Plum
Responsible Plum
Language models Plum
Let's treat language model tests as professionally as we treat exams
  • Bachmann, et al.
  • Published in 2024
Language models Plum
Bias Plum
Theory-driven Plum
Tackling Language Modelling Bias in Support of Linguistic Diversity
  • Gabor Bella, Paula Helm, Gertraud Koch, Fausto Giunchiglia
  • Published in 2024
Responsible Plum
Language models Plum
Fairness Plum
Bias Plum
Inclusive Plum
Diversity and language technology: how language modeling bias causes epistemic injustice
  • Helm, Bella, Koch, & Giunchiglia
  • Published in 2024
Responsible Plum
Language models Plum
Fairness Plum
Bias Plum
Inclusive Plum
Are LLMs classical or nonmonotonic reasoners? Lessons from generics
  • Alina Leidinger, Robert van Rooij, Ekaterina Shutova
  • Published in 2024
Trustworthy Plum
Responsible Plum
Language models Plum

About the people

CERTAIN consists of a diverse group of researchers with various backgrounds. What unites us is our interest in developing explainable and responsible AI. Feel free to contact us or learn more about what we do.

Browse all people

Jelke Bloem

Assistant Professor

J.Bloem@uva.nl
Visit personal website
More information

Jelle Zuidema

Associate Professor

j.zuidema@uva.nl
Visit personal website
More information

Gabriel Pereira

Assistant Professor

g.pereira@uva.nl
Visit personal website
More information

Blogs & events

Using Language Sciences for Social Good

Language technologies, like ChatGPT, are developing quickly. But we don’t really know how they work. And they are not always designed to help society. adapted from Nikki Weststeijn‘s post on...

Going beyond a mathematical investigation of bias

A version of this blog post first appeared on https://odvanderwal.nl/2023/positioning-bias. When researchers study how biased language models are, they generally approach this in a mathematical or statistical way. For example,...