Publications d'Andreas Madsen

Andreas Madsen

Co-superviseur: Siva Reddy
Domaines de recherche: Interprétabilité de traitement du langage naturel

Activité

Interpretability Needs a New Paradigm
Andreas Madsen, Himabindu Lakkaraju, Siva Reddy et Sarath Chandar
In ArXiv, 2024.
#NLP, #DL, #Other
[arXiv]

Are self-explanations from Large Language Models faithful?
Andreas Madsen, Sarath Chandar et Siva Reddy
Findings of the Association for Computational Linguistics (ACL), 2024.
#NLP
[arXiv], [code]
Faithfulness Measurable Masked Language Models
Andreas Madsen, Siva Reddy et Sarath Chandar
International Conference on Machine Learning (ICML), 2024. [Spotlight award - top 3.5%]
#NLP
[arXiv], [code], [YouTube], [blogpost]

Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining
Andreas Madsen, Nicholas Meade, Vaibhav Adlakha et Siva Reddy
Findings of the Association for Computational Linguistics (EMNLP), 2022.
[BlackboxNLP Workshop, 2022]
#NLP
[arXiv], [code]
Post-hoc Interpretability for Neural NLP: A Survey
Andreas Madsen, Siva Reddy et Sarath Chandar
ACM Computing Surveys, 2022.
#NLP
[arXiv]