| Beyond the imitation game: Quantifying and extrapolating the capabilities of language models A Srivastava, A Rastogi, A Rao, AAM Shoeb, A Abid, A Fisch, AR Brown, ... arXiv preprint arXiv:2206.04615, 2022 | 879 | 2022 |
| Compositionality decomposed: How do neural networks generalise? D Hupkes, V Dankers, M Mul, E Bruni Journal of Artificial Intelligence Research 67, 757-795, 2020 | 326* | 2020 |
| Visualisation and'diagnostic classifiers' reveal how recurrent and recursive neural networks process hierarchical structure D Hupkes, S Veldhoen, W Zuidema Journal of Artificial Intelligence Research 61, 907-926, 2018 | 289 | 2018 |
| Masked language modeling and the distributional hypothesis: Order word matters pre-training for little K Sinha, R Jia, D Hupkes, J Pineau, A Williams, D Kiela arXiv preprint arXiv:2104.06644, 2021 | 229 | 2021 |
| The emergence of number and syntax units in LSTM language models Y Lakretz, G Kruszewski, T Desbordes, D Hupkes, S Dehaene, M Baroni arXiv preprint arXiv:1903.07435, 2019 | 186 | 2019 |
| Under the hood: Using diagnostic classifiers to investigate and improve how language models track agreement information M Giulianelli, J Harding, F Mohnert, D Hupkes, W Zuidema arXiv preprint arXiv:1808.08079, 2018 | 172 | 2018 |
| A taxonomy and review of generalization research in NLP D Hupkes, M Giulianelli, V Dankers, M Artetxe, Y Elazar, T Pimentel, ... Nature Machine Intelligence 5 (10), 1161-1174, 2023 | 86* | 2023 |
| Mechanisms for handling nested dependencies in neural-network language models and humans Y Lakretz, D Hupkes, A Vergallito, M Marelli, M Baroni, S Dehaene Cognition 213, 104699, 2021 | 70 | 2021 |
| Do language models understand anything? On the ability of LSTMs to understand negative polarity items J Jumelet, D Hupkes arXiv preprint arXiv:1808.10627, 2018 | 62 | 2018 |
| The paradox of the compositionality of natural language: A neural machine translation case study V Dankers, E Bruni, D Hupkes arXiv preprint arXiv:2108.05885, 2021 | 59 | 2021 |
| Diagnostic Classifiers Revealing how Neural Networks Process Hierarchical Structure. S Veldhoen, D Hupkes, WH Zuidema CoCo@ NIPS, 69-77, 2016 | 51 | 2016 |
| Analysing neural language models: Contextual decomposition reveals default reasoning in number and gender assignment J Jumelet, W Zuidema, D Hupkes arXiv preprint arXiv:1909.08975, 2019 | 44 | 2019 |
| Co-evolution of language and agents in referential games G Dagan, D Hupkes, E Bruni arXiv preprint arXiv:2001.03361, 2020 | 37 | 2020 |
| Location attention for extrapolation to longer sequences Y Dubois, G Dagan, D Hupkes, E Bruni arXiv preprint arXiv:1911.03872, 2019 | 32 | 2019 |
| Learning compositionally through attentive guidance D Hupkes, A Singh, K Korrel, G Kruszewski, E Bruni arXiv preprint arXiv:1805.09657, 2018 | 31 | 2018 |
| Transcoding compositionally: Using attention to find more generalizable solutions K Korrel, D Hupkes, V Dankers, E Bruni arXiv preprint arXiv:1906.01234, 2019 | 30 | 2019 |
| Language models use monotonicity to assess NPI licensing J Jumelet, M Denić, J Szymanik, D Hupkes, S Steinert-Threlkeld arXiv preprint arXiv:2105.13818, 2021 | 25 | 2021 |
| How bpe affects memorization in transformers E Kharitonov, M Baroni, D Hupkes arXiv preprint arXiv:2110.02782, 2021 | 23 | 2021 |
| Generalising to German plural noun classes, from the perspective of a recurrent neural network V Dankers, A Langedijk, K McCurdy, A Williams, D Hupkes Proceedings of the 25th Conference on Computational Natural Language …, 2021 | 22 | 2021 |
| Sparse interventions in language models with differentiable masking N De Cao, L Schmid, D Hupkes, I Titov arXiv preprint arXiv:2112.06837, 2021 | 21 | 2021 |
