Publications d'Andreas Madsen
-
Andreas Madsen
Co-superviseur: Siva Reddy
Domaines de recherche: Interprétabilité de traitement du langage naturel
Activité
- Étudiant au doctorat: août 2020 - maintenant
Prépublications
-
Are self-explanations from Large Language Models faithful?
Andreas Madsen, Sarath Chandar et Siva Reddy
In ArXiv, 2024.
#NLP
[arXiv], [code] -
Faithfulness Measurable Masked Language Models
Andreas Madsen, Siva Reddy et Sarath Chandar
In ArXiv, 2023.
#NLP
[arXiv], [code], [YouTube]
Articles de conférence et de revue
2022
-
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 Empirical Methods in Natural Language Processing (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]