Post-hoc Interpretability for Neural NLP: A survey A Madsen, S Reddy, S Chandar ACM Computing Surveys (CSUR) 55 (8), 1-42, 2022 | 223 | 2022 |
Neural Arithmetic Units A Madsen, AR Johansen International Conference on Learning Representations (ICLR) - [spotlight award], 2020 | 54 | 2020 |
Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining A Madsen, N Meade, V Adlakha, S Reddy Empirical Methods in Natural Language Processing (EMNLP 2022 and BlacboxNLP), 2022 | 33 | 2022 |
Visualizing memorization in RNNs A Madsen Distill Journal 4 (3), e16, 2019 | 31 | 2019 |
Measuring Arithmetic Extrapolation Performance A Madsen, AR Johansen SEDL Workshop at Conference on Neural Information Processing Systems (NeurIPS), 2019 | 10 | 2019 |
Are self-explanations from Large Language Models faithful? A Madsen, S Chandar, S Reddy Annual Meeting of the Association for Computational Linguistics (ACL 2024), 2024 | 6* | 2024 |
Faithfulness Measurable Masked Language Models A Madsen, S Reddy, S Chandar International Conference on Machine Learning (ICML 2024) - [spotlight award], 2023 | 3 | 2023 |
Interpretability Needs a New Paradigm A Madsen, H Lakkaraju, S Reddy, S Chandar arXiv preprint arXiv:2405.05386, 2024 | 2 | 2024 |