| The llama 3 herd of models A Grattafiori, A Dubey, A Jauhri, A Pandey, A Kadian, A Al-Dahle, ... arXiv preprint arXiv:2407.21783, 2024 | 3641 | 2024 |
| Don't stop pretraining: Adapt language models to domains and tasks S Gururangan, A Marasović, S Swayamdipta, K Lo, I Beltagy, D Downey, ... arXiv preprint arXiv:2004.10964, 2020 | 2577 | 2020 |
| Annotation artifacts in natural language inference data S Gururangan, S Swayamdipta, O Levy, R Schwartz, SR Bowman, ... arXiv preprint arXiv:1803.02324, 2018 | 1300 | 2018 |
| Realtoxicityprompts: Evaluating neural toxic degeneration in language models S Gehman, S Gururangan, M Sap, Y Choi, NA Smith arXiv preprint arXiv:2009.11462, 2020 | 1199 | 2020 |
| Editing models with task arithmetic G Ilharco, MT Ribeiro, M Wortsman, S Gururangan, L Schmidt, ... arXiv preprint arXiv:2212.04089, 2022 | 545 | 2022 |
| All that's' human'is not gold: Evaluating human evaluation of generated text E Clark, T August, S Serrano, N Haduong, S Gururangan, NA Smith arXiv preprint arXiv:2107.00061, 2021 | 433 | 2021 |
| Show your work: Improved reporting of experimental results J Dodge, S Gururangan, D Card, R Schwartz, NA Smith arXiv preprint arXiv:1909.03004, 2019 | 287 | 2019 |
| Less: Selecting influential data for targeted instruction tuning M Xia, S Malladi, S Gururangan, S Arora, D Chen arXiv preprint arXiv:2402.04333, 2024 | 170 | 2024 |
| Branch-train-merge: Embarrassingly parallel training of expert language models M Li, S Gururangan, T Dettmers, M Lewis, T Althoff, NA Smith, ... arXiv preprint arXiv:2208.03306, 2022 | 162 | 2022 |
| Variational pretraining for semi-supervised text classification S Gururangan, T Dang, D Card, NA Smith arXiv preprint arXiv:1906.02242, 2019 | 145 | 2019 |
| Detoxifying language models risks marginalizing minority voices A Xu, E Pathak, E Wallace, S Gururangan, M Sap, D Klein arXiv preprint arXiv:2104.06390, 2021 | 137 | 2021 |
| Demix layers: Disentangling domains for modular language modeling S Gururangan, M Lewis, A Holtzman, NA Smith, L Zettlemoyer arXiv preprint arXiv:2108.05036, 2021 | 123 | 2021 |
| Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments T Xie, D Zhang, J Chen, X Li, S Zhao, R Cao, JH Toh, Z Cheng, D Shin, ... Advances in Neural Information Processing Systems 37, 52040-52094, 2024 | 93 | 2024 |
| Time waits for no one! analysis and challenges of temporal misalignment K Luu, D Khashabi, S Gururangan, K Mandyam, NA Smith arXiv preprint arXiv:2111.07408, 2021 | 86 | 2021 |
| Silo language models: Isolating legal risk in a nonparametric datastore S Min, S Gururangan, E Wallace, W Shi, H Hajishirzi, NA Smith, ... arXiv preprint arXiv:2308.04430, 2023 | 68 | 2023 |
| Datacomp-lm: In search of the next generation of training sets for language models J Li, A Fang, G Smyrnis, M Ivgi, M Jordan, SY Gadre, H Bansal, E Guha, ... Advances in Neural Information Processing Systems 37, 14200-14282, 2024 | 58 | 2024 |
| Nearest neighbor zero-shot inference W Shi, J Michael, S Gururangan, L Zettlemoyer Proceedings of the 2022 Conference on Empirical Methods in Natural Language …, 2022 | 53 | 2022 |
| Scaling expert language models with unsupervised domain discovery S Gururangan, M Li, M Lewis, W Shi, T Althoff, NA Smith, L Zettlemoyer arXiv preprint arXiv:2303.14177, 2023 | 43 | 2023 |
| Whose language counts as high quality? Measuring language ideologies in text data selection S Gururangan, D Card, SK Dreier, EK Gade, LZ Wang, Z Wang, ... arXiv preprint arXiv:2201.10474, 2022 | 29 | 2022 |
| Language models scale reliably with over-training and on downstream tasks SY Gadre, G Smyrnis, V Shankar, S Gururangan, M Wortsman, R Shao, ... arXiv preprint arXiv:2403.08540, 2024 | 28 | 2024 |
Noah A. SmithUniversity of Washington; Allen Institute for Artificial IntelligenceVerified email at cs.washington.edu
