activity
20222025
most citedThe Birth of Bias: A case study on the evolution of gender bias in an English language model

2 citations · 2 across the 7 of their papers we have counts for

collaborators

7 papers

cs.LG2025

Propositional Logic for Probing Generalization in Neural Networks

Anna Langedijk, Jaap Jumelet, Willem Zuidema

The extent to which neural networks are able to acquire and represent symbolic rules remains a key topic of research and debate. Much current work focuses on the impressive capabil…

cs.CL2024

Finding Structure in Language Models

Jaap Jumelet

When we speak, write or listen, we continuously make predictions based on our knowledge of a language's grammar. Remarkably, children acquire this grammatical knowledge within just…

cs.CL2024

Interpretability of Language Models via Task Spaces

Lucas Weber, Jaap Jumelet, Elia Bruni +1

The usual way to interpret language models (LMs) is to test their performance on different benchmarks and subsequently infer their internal processes. In this paper, we present an…

cs.CL2023

Transparency at the Source: Evaluating and Interpreting Language Models With Access to the True Distribution

Jaap Jumelet, Willem Zuidema

We present a setup for training, evaluating and interpreting neural language models, that uses artificial, language-like data. The data is generated using a massive probabilistic g…

cs.CL2023

ChapGTP, ILLC's Attempt at Raising a BabyLM: Improving Data Efficiency by Automatic Task Formation

Jaap Jumelet, Michael Hanna, Marianne de Heer Kloots +3

We present the submission of the ILLC at the University of Amsterdam to the BabyLM challenge (Warstadt et al., 2023), in the strict-small track. Our final model, ChapGTP, is a mask…

cs.LG2023

Curriculum Learning with Adam: The Devil Is in the Wrong Details

Lucas Weber, Jaap Jumelet, Paul Michel +2

Curriculum learning (CL) posits that machine learning models -- similar to humans -- may learn more efficiently from data that match their current learning progress. However, CL me…