| Transformers Can Represent -gram Language Models A Svete, R Cotterell arXiv preprint arXiv:2404.14994, 2024 | 35 | 2024 |
| Formal aspects of language modeling R Cotterell, A Svete, C Meister, T Liu, L Du arXiv preprint arXiv:2311.04329, 2023 | 20 | 2023 |
| On the representational capacity of neural language models with chain-of-thought reasoning F Nowak, A Svete, A Butoi, R Cotterell arXiv preprint arXiv:2406.14197, 2024 | 19 | 2024 |
| What languages are easy to language-model? a perspective from learning probabilistic regular languages N Borenstein, A Svete, R Chan, J Valvoda, F Nowak, I Augenstein, ... arXiv preprint arXiv:2406.04289, 2024 | 18 | 2024 |
| A geometric notion of causal probing C Guerner, A Svete, T Liu, A Warstadt, R Cotterell arXiv preprint arXiv:2307.15054, 2023 | 17 | 2023 |
| Recurrent neural language models as probabilistic finite-state automata A Svete, R Cotterell arXiv preprint arXiv:2310.05161, 2023 | 16 | 2023 |
| On the representational capacity of recurrent neural language models F Nowak, A Svete, L Du, R Cotterell arXiv preprint arXiv:2310.12942, 2023 | 15 | 2023 |
| Training neural networks as recognizers of formal languages A Butoi, G Khalighinejad, A Svete, J Valvoda, R Cotterell, B DuSell arXiv preprint arXiv:2411.07107, 2024 | 12 | 2024 |
| Can Transformers Learn -gram Language Models? A Svete, N Borenstein, M Zhou, I Augenstein, R Cotterell arXiv preprint arXiv:2410.03001, 2024 | 11 | 2024 |
| Gumbel counterfactual generation from language models S Ravfogel, A Svete, V Snæbjarnarson, R Cotterell arXiv preprint arXiv:2411.07180, 2024 | 10 | 2024 |
| The Role of -gram Smoothing in the Age of Neural Networks L Malagutti, A Buinovskij, A Svete, C Meister, A Amini, R Cotterell arXiv preprint arXiv:2403.17240, 2024 | 9 | 2024 |
| Lower bounds on the expressivity of recurrent neural language models A Svete, F Nowak, A Sahabdeen, R Cotterell Proceedings of the 2024 Conference of the North American Chapter of the …, 2024 | 7 | 2024 |
| A theoretical result on the inductive bias of RNN language models A Svete, RSM Chan, R Cotterell CoRR, 2024 | 5 | 2024 |
| Unique Hard Attention: A Tale of Two Sides S Jerad, A Svete, J Li, R Cotterell arXiv preprint arXiv:2503.14615, 2025 | 4 | 2025 |
| Efficiently Representing Finite-state Automata With Recurrent Neural Networks A Svete, R Cotterell arXiv preprint arXiv:2310.05161v3, 2023 | 4 | 2023 |
| Algorithms for acyclic weighted finite-state automata with failure arcs A Svete, B Dayan, R Cotterell, T Vieira, J Eisner Proceedings of the 2022 Conference on Empirical Methods in Natural Language …, 2022 | 4 | 2022 |
| It is not just about the melody: how Europe votes for its favorite songs A Svete, J Hostnik arXiv preprint arXiv:2002.06609, 2020 | 4 | 2020 |
| Counterfactual generation from language models S Ravfogel, A Svete, V Snæbjarnarson, R Cotterell arXiv e-prints, arXiv: 2411.07180, 2024 | 3 | 2024 |
| On efficiently representing regular languages as RNNs A Svete, R Chan, R Cotterell Findings of the Association for Computational Linguistics: ACL 2024, 4118-4135, 2024 | 3 | 2024 |
| Information locality as an inductive bias for neural language models T Someya, A Svete, B DuSell, T O’Donnell, M Giulianelli, R Cotterell Proceedings of the 63rd Annual Meeting of the Association for Computational …, 2025 | 2 | 2025 |
Ryan CotterellETH ZürichVerified email at inf.ethz.ch
