| Bloom: A 176b-parameter open-access multilingual language model T Le Scao, A Fan, C Akiki, E Pavlick, S Ilić, D Hesslow, R Castagné, ... | 1747 | 2023 |
| Dynabench: Rethinking benchmarking in NLP D Kiela, M Bartolo, Y Nie, D Kaushik, A Geiger, Z Wu, B Vidgen, G Prasad, ... NAACL, 2021 | 426 | 2021 |
| Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality T Thrush*, R Jiang, M Bartolo, A Singh, A Williams, D Kiela, C Ross* CVPR, 2022 | 393 | 2022 |
| Learning from the worst: Dynamically generated datasets to improve online hate detection B Vidgen, T Thrush, Z Waseem, D Kiela ACL, 2021 | 260 | 2021 |
| TRL: Transformer reinforcement learning L von Werra, Y Belkada, L Tunstall, E Beeching, T Thrush, N Lambert GitHub. Available online at: https://github.com/lvwerra/trl, 2020 | 210 | 2020 |
| The BigScience ROOTS Corpus: A 1.6 TB Composite Multilingual Dataset H Laurençon, L Saulnier, T Wang, C Akiki, AV del Moral, T Le Scao, ... NeurIPS Datasets and Benchmarks, 2022 | 190 | 2022 |
| DataPerf: Benchmarks for Data-Centric AI Development M Mazumder, C Banbury, X Yao, B Karlaš, WG Rojas, S Diamos, ... NeurIPS Datasets and Benchmarks, 2024 | 144 | 2024 |
| Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation M Bartolo, T Thrush, R Jia, S Riedel, P Stenetorp, D Kiela EMNLP, 2021 | 98 | 2021 |
| Human-adversarial visual question answering S Sheng, A Singh, V Goswami, JAL Magana, T Thrush, W Galuba, ... NeurIPS, 2021 | 67 | 2021 |
| Hatemoji: A Test Suite and Adversarially-Generated Dataset for Benchmarking and Detecting Emoji-based Hate HR Kirk, B Vidgen, P Röttger, T Thrush, SA Hale NAACL, 2022 | 63 | 2022 |
| Dynaboard: An Evaluation-As-A-Service Platform for Holistic Next-Generation Benchmarking Z Ma*, K Ethayarajh*, T Thrush*, S Jain, L Wu, R Jia, C Potts, A Williams, ... NeurIPS, 2021 | 62 | 2021 |
| Towards language models that can see: Computer vision through the lens of natural language W Berrios, G Mittal, T Thrush, D Kiela, A Singh arXiv preprint arXiv:2306.16410, 2023 | 59 | 2023 |
| Anlizing the adversarial natural language inference dataset A Williams, T Thrush, D Kiela SCiL, 2022 | 43 | 2022 |
| Measuring data M Mitchell, AS Luccioni, N Lambert, M Gerchick, A McMillan-Major, ... arXiv preprint arXiv:2212.05129, 2022 | 37 | 2022 |
| Huggingface h4 stack exchange preference dataset N Lambert, L Tunstall, N Rajani, T Thrush https://huggingface.co/datasets/HuggingFaceH4/stack-exchange-preferences, 2023 | 36* | 2023 |
| Models in the Loop: Aiding Crowdworkers with Generative Annotation Assistants M Bartolo, T Thrush, S Riedel, P Stenetorp, R Jia, D Kiela NAACL, 2022 | 36 | 2022 |
| Evaluate & Evaluation on the Hub: Better Best Practices for Data and Model Measurement L von Werra, L Tunstall, A Thakur, AS Luccioni, T Thrush, A Piktus, ... EMNLP System Demos, 2022 | 24 | 2022 |
| Findings of the WMT 2021 Shared Task on Large-Scale Multilingual Machine Translation G Wenzek, V Chaudhary, A Fan, S Gomez, N Goyal, S Jain, D Kiela, ... WMT at EMNLP, 2021 | 21 | 2021 |
| Investigating Novel Verb Learning in BERT: Selectional Preference Classes and Alternation-Based Syntactic Generalization T Thrush, E Wilcox, R Levy BlackboxNLP at EMNLP, 2020 | 20 | 2020 |
| Dynatask: A Framework for Creating Dynamic AI Benchmark Tasks T Thrush, K Tirumala, A Gupta, M Bartolo, P Rodriguez, T Kane, ... ACL System Demos, 2022 | 17 | 2022 |
Douwe KielaContextual AI, Stanford University在 stanford.edu 的电子邮件经过验证