<  Retour au portail Polytechnique Montréal

Documents dont l'auteur est "Madsen, Andreas"

Monter d'un niveau
Pour citer ou exporter [feed] Atom [feed] RSS 1.0 [feed] RSS 2.0
Nombre de documents: 4

Madsen, A., Anbil Parthipan, S. C., & Reddy, S. (août 2024). Are self-explanations from Large Language Models faithful? [Communication écrite]. 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024), Hybrid, Bangkok, Thailand. Lien externe

Madsen, A., Reddy, S., & Anbil Parthipan, S. C. (juillet 2024). Faithfulness Measurable Masked Language Models [Communication écrite]. 41st International Conference on Machine Learning (ICML 2024), Vienna, Austria. Lien externe

Madsen, A., Reddy, S., & Anbil Parthipan, S. C. (2023). Post-hoc Interpretability for Neural NLP: A Survey. ACM Computing Surveys, 55(8), 1-42. Lien externe

Madsen, A., Meade, N., Adlakha, V., & Reddy, S. (décembre 2022). Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining [Communication écrite]. Findings of the Association for Computational Linguistics (EMNLP 2022), Abu Dhabi, United Arab Emirates. Lien externe

Liste produite: Sun Nov 24 05:13:41 2024 EST.