Evaluating self-attention interpretability through human-grounded experimental protocol M Bhan, N Achache, V Legrand, A Blangero, N Chesneau Explainable Artificial Intelligence. xAI 2023, 2023 | 4 | 2023 |
TIGTEC: Token Importance Guided TExt Counterfactuals M Bhan, JN Vittaut, N Chesneau, MJ Lesot Machine Learning and Knowledge Discovery in Databases: Research Track …, 2023 | 3 | 2023 |
Self-AMPLIFY: Improving Small Language Models with Self Post Hoc Explanations M Bhan, JN Vittaut, N Chesneau, MJ Lesot arXiv preprint arXiv:2402.12038, 2024 | | 2024 |
Enhancing textual counterfactual explanation intelligibility through Counterfactual Feature Importance B Milan, V Jean-Noel, C Nicolas, L Marie-Jeanne ACL - Proceedings of the 3rd Workshop on Trustworthy Natural Language …, 2023 | | 2023 |