Andreas Madsen

According to our database, Andreas Madsen authored at least 6 papers between 2019 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2024

Are self-explanations from Large Language Models faithful?

Andreas Madsen, Sarath Chandar, Siva Reddy

CoRR, 2024

2023

Post-hoc Interpretability for Neural NLP: A Survey.

Andreas Madsen, Siva Reddy, Sarath Chandar

ACM Comput. Surv., 2023

Faithfulness Measurable Masked Language Models.

Andreas Madsen, Siva Reddy, Sarath Chandar

CoRR, 2023

2022

Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining.

Andreas Madsen, Nicholas Meade, Vaibhav Adlakha, Siva Reddy

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2022, 2022

2020

Neural Arithmetic Units.

Andreas Madsen, Alexander Rosenberg Johansen

Proceedings of the 8th International Conference on Learning Representations, 2020

2019

Measuring Arithmetic Extrapolation Performance.

Andreas Madsen, Alexander Rosenberg Johansen

CoRR, 2019