| 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, ... TMLR 2023. Finalist for Outstanding Certification, 2022 | 1238 | 2022 |
| Transformer feed-forward layers are key-value memories M Geva, R Schuster, J Berant, O Levy EMNLP 2021, 2020 | 656 | 2020 |
| Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies M Geva, D Khashabi, E Segal, T Khot, D Roth, J Berant Transactions of the Association for Computational Linguistics 9, 346-361, 2021 | 543 | 2021 |
| Are we modeling the task or the annotator? an investigation of annotator bias in natural language understanding datasets M Geva, Y Goldberg, J Berant EMNLP 2019, 2019 | 374 | 2019 |
| Transformer feed-forward layers build predictions by promoting concepts in the vocabulary space M Geva, A Caciularu, KR Wang, Y Goldberg EMNLP 2022, 2022 | 262 | 2022 |
| Injecting Numerical Reasoning Skills into Language Models M Geva, A Gupta, J Berant ACL 2020, 2020 | 233 | 2020 |
| Break It Down: A Question Understanding Benchmark T Wolfson, M Geva, A Gupta, M Gardner, Y Goldberg, D Deutch, J Berant TACL, 2020 | 186 | 2020 |
| Dissecting recall of factual associations in auto-regressive language models M Geva, J Bastings, K Filippova, A Globerson EMNLP 2023, 2023 | 180 | 2023 |
| Scrolls: Standardized comparison over long language sequences U Shaham, E Segal, M Ivgi, A Efrat, O Yoran, A Haviv, A Gupta, W Xiong, ... EMNLP 2022, 2022 | 129 | 2022 |
| Analyzing transformers in embedding space G Dar, M Geva, A Gupta, J Berant ACL 2023, 2022 | 111 | 2022 |
| Evaluating the ripple effects of knowledge editing in language models R Cohen, E Biran, O Yoran, A Globerson, M Geva Transactions of the Association for Computational Linguistics 12, 283-298, 2024 | 102 | 2024 |
| Lm vs lm: Detecting factual errors via cross examination R Cohen, M Hamri, M Geva, A Globerson EMNLP 2023, 2023 | 98 | 2023 |
| In-context learning creates task vectors R Hendel, M Geva, A Globerson Findings of EMNLP 2023, 2023 | 91 | 2023 |
| Crawling the internal knowledge-base of language models R Cohen, M Geva, J Berant, A Globerson Findings of EACL 2023, 2023 | 72 | 2023 |
| Don't Blame the Annotator: Bias Already Starts in the Annotation Instructions M Parmar, S Mishra, M Geva, C Baral EACL 2023. Outstanding Paper Award, 2022 | 62 | 2022 |
| DiscoFuse: A Large-Scale Dataset for Discourse-based Sentence Fusion M Geva, E Malmi, I Szpektor, J Berant NAACL-HLT 2019 1, 3443-3455, 2019 | 56 | 2019 |
| Emergence of communication in an interactive world with consistent speakers B Bogin, M Geva, J Berant Emergent Communication Workshop, NIPS 2018, 2018 | 46* | 2018 |
| Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models A Ghandeharioun, A Caciularu, A Pearce, L Dixon, M Geva ICML 2024, 2024 | 42 | 2024 |
| Lm-debugger: An interactive tool for inspection and intervention in transformer-based language models M Geva, A Caciularu, G Dar, P Roit, S Sadde, M Shlain, B Tamir, ... System Demonstrations Track, EMNLP 2022, 2022 | 41 | 2022 |
| Jump to Conclusions: Short-Cutting Transformers With Linear Transformations A Yom Din, T Karidi, L Choshen, M Geva LREC-COLING 2024, arXiv: 2303.09435, 2023 | 39* | 2023 |
Jonathan BerantAssociate Professor, Tel-Aviv University, Visiting Faculty Researcher, Google DeepMIndVerified email at cs.tau.ac.il
