| Meta-learning via Language Model In-context Tuning Y Chen, R Zhong, S Zha, G Karypis, H He ACL 2022, 2022 | 196 | 2022 |
| Reasoning Models Don't Always Say What They Think Y Chen, J Benton, A Radhakrishnan, J Uesato, C Denison, J Schulman, ... arXiv preprint arXiv:2505.05410, 2025 | 167 | 2025 |
| On the relation between sensitivity and accuracy in in-context learning Y Chen, C Zhao, Z Yu, K McKeown, H He EMNLP 2023 Findings, 2022 | 90 | 2022 |
| Do models explain themselves? counterfactual simulatability of natural language explanations Y Chen, R Zhong, N Ri, C Zhao, H He, J Steinhardt, Z Yu, K McKeown ICML 2024 Spotlight, 2023 | 89 | 2023 |
| In-context learning distillation: Transferring few-shot learning ability of pre-trained language models Y Huang, Y Chen, Z Yu, K McKeown arXiv preprint arXiv:2212.10670, 2022 | 74 | 2022 |
| Parallel Structures in Pre-training Data Yield In-Context Learning Y Chen, C Zhao, Z Yu, K McKeown, H He ACL 2024, 2024 | 27 | 2024 |
| Towards consistent natural-language explanations via explanation-consistency finetuning Y Chen, C Singh, X Liu, S Zuo, B Yu, H He, J Gao COLING 2025, 2024 | 21 | 2024 |
| Inverse scaling in test-time compute AP Gema, A Hägele, R Chen, A Arditi, J Goldman-Wetzler, ... arXiv preprint arXiv:2507.14417, 2025 | 17 | 2025 |
| Cross-language Sentence Selection via Data Augmentation and Rationale Training Y Chen, C Kedzie, S Nair, P Galuščáková, R Zhang, DW Oard, ... ACL 2021, 2021 | 13 | 2021 |
| Detecting and reducing bias in a high stakes domain R Zhong, Y Chen, D Patton, C Selous, K McKeown EMNLP 2019, 2019 | 6 | 2019 |
| Enhancing Model Safety through Pretraining Data Filtering Y Chen, M Tucker, N Panickssery, T Wang, F Mosconi, A Gopal, ... Anthropic Alignment Science Blog, 2025 | 5 | 2025 |
| Social Orientation: A New Feature for Dialogue Analysis T Morrill, Z Deng, Y Chen, A Ananthram, CW Leach, K McKeown LREC-Coling 2024, 2024 | 5 | 2024 |
| Improved Synthetic Training for Reading Comprehension Y Chen, MA Sultan, V Castelli arXiv preprint arXiv:2010.12776, 2020 | 2 | 2020 |
| Counterfactual Simulatability of LLM Explanations for Generation Tasks M Limpijankit, Y Chen, M Subbiah, N Deas, K McKeown arXiv preprint arXiv:2505.21740, 2025 | 1 | 2025 |
Kathleen McKeownProfessor of Computer Science and Director, Data Science Institute, Columbia UniversityVerified email at cs.columbia.edu
