Picking BERT's brain: Probing for linguistic dependencies in contextualized embeddings using representational similarity analysis MA Lepori, RT McCoy arXiv preprint arXiv:2011.12073, 2020 | 24 | 2020 |
Break it down: Evidence for structural compositionality in neural networks M Lepori, T Serre, E Pavlick Advances in Neural Information Processing Systems 36, 42623-42660, 2023 | 20 | 2023 |
Unequal representations: Analyzing intersectional biases in word embeddings using representational similarity analysis MA Lepori arXiv preprint arXiv:2011.12086, 2020 | 18 | 2020 |
Representations of syntax [MASK] useful: Effects of constituency and dependency structure in recursive LSTMs MA Lepori, T Linzen, RT McCoy arXiv preprint arXiv:2005.00019, 2020 | 14 | 2020 |
Can You Hear Me Now? Sensitive Comparisons of Human and Machine Perception MA Lepori, C Firestone Cognitive Science 46 (10), e13191, 2022 | 8 | 2022 |
NeuroSurgeon: A toolkit for subnetwork analysis MA Lepori, E Pavlick, T Serre arXiv preprint arXiv:2309.00244, 2023 | 6 | 2023 |
Deep neural networks can learn generalizable same-different visual relations AR Tartaglini, S Feucht, MA Lepori, WK Vong, C Lovering, BM Lake, ... arXiv preprint arXiv:2310.09612, 2023 | 4 | 2023 |
Uncovering Intermediate Variables in Transformers using Circuit Probing MA Lepori, T Serre, E Pavlick arXiv preprint arXiv:2311.04354, 2023 | 3* | 2023 |
Noise2Astro: Astronomical Image Denoising with Self-supervised Neural Networks Y Zhang, B Nord, A Pagul, M Lepori Research Notes of the AAS 6 (9), 187, 2022 | 3 | 2022 |
Dual Process Learning: Controlling Use of In-Context vs. In-Weights Strategies with Weight Forgetting S Anand, MA Lepori, J Merullo, E Pavlick arXiv preprint arXiv:2406.00053, 2024 | 2 | 2024 |
Instilling inductive biases with subnetworks E Zhang, MA Lepori, E Pavlick arXiv preprint arXiv:2310.10899, 2023 | 2 | 2023 |
Who's asking? User personas and the mechanics of latent misalignment A Ghandeharioun, A Yuan, M Guerard, E Reif, MA Lepori, L Dixon arXiv preprint arXiv:2406.12094, 2024 | 1 | 2024 |
Are LLMs Models of Distributional Semantics? A Case Study on Quantifiers Z Enyan, Z Wang, MA Lepori, E Pavlick, H Aparicio arXiv preprint arXiv:2410.13984, 2024 | | 2024 |
Racing Thoughts: Explaining Large Language Model Contextualization Errors MA Lepori, M Mozer, A Ghandeharioun arXiv preprint arXiv:2410.02102, 2024 | | 2024 |
Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects MA Lepori, AR Tartaglini, WK Vong, T Serre, BM Lake, E Pavlick arXiv preprint arXiv:2406.15955, 2024 | | 2024 |
Which “shoe” is best? Humans know what good training examples look like M Nartker, M Lepori, C Firestone Journal of Vision 20 (11), 1318-1318, 2020 | | 2020 |
Cell Response to Liquid Crystal Order KD Endresen, F Serra, MA Lepori Biophysical Journal 116 (3), 546a, 2019 | | 2019 |