AIConfPaper
← Search

Karel D'Oosterlinck

4 accepted papers

2025

HyperDAS: Towards Automating Mechanistic Interpretability with Hypernetworks

Jiuding Sun, Jing Huang, Sidharth Baskaran, Karel D'Oosterlinck, Christopher Potts, Michael Sklar +1
ICLR 2025poster

Mechanistic interpretability has made great strides in identifying neural network features (e.g., directions in hidden activation space) that mediate concepts (e.g., *the birth year of a Nobel laureate*) and enable predictable manipulation. Distributed alignment search (DAS) leverages supervision fr…

Cited by 0Source ↗PDF ↗Scholar ↗
2023

BioDEX: Large-Scale Biomedical Adverse Drug Event Extraction for Real-World Pharmacovigilance

Karel D'Oosterlinck, François Remy, Johannes Deleu, Thomas Demeester, Chris Develder, Klim Zaporojets +4
EMNLP 2023long findings

Timely and accurate extraction of Adverse Drug Events (ADE) from biomedical literature is paramount for public safety, but involves slow and costly manual labor. We set out to improve drug safety monitoring (pharmacovigilance, PV) through the use of Natural Language Processing (NLP). We introduce Bi…

Cited by 0Source ↗code ↗Scholar ↗
2023

Causal Proxy Models for Concept-based Model Explanations

Zhengxuan Wu, Karel D'Oosterlinck, Atticus Geiger, Amir Zur, Christopher Potts
ICML 2023poster

Explainability methods for NLP systems encounter a version of the fundamental problem of causal inference: for a given ground-truth input text, we never truly observe the counterfactual texts necessary for isolating the causal effects of model representations on outputs. In response, many explainabi…

Cited by 40Source ↗PDF ↗code ↗Scholar ↗
2022

CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior

Eldar David Abraham, Karel D'Oosterlinck, Amir Feder, Yair Ori Gat, Atticus Geiger, Christopher Potts +2
NeurIPS 2022accept

The increasing size and complexity of modern ML systems has improved their predictive capabilities but made their behavior harder to explain. Many techniques for model explanation have been developed in response, but we lack clear criteria for assessing these techniques. In this paper, we cast model…

Cited by 54Source ↗PDF ↗Scholar ↗