| Unsupervised data augmentation for consistency training MQ Shieh, Z Dai, E Hovy, MT Luong, QV Le NeurIPS 2020, 2019 | 3486* | 2019 |
| Self-training with noisy student improves imagenet classification MQ Shieh, MT Luong, E Hovy, QV Le CVPR 2020, 2020 | 3452 | 2020 |
| Race: Large-scale reading comprehension dataset from examinations G Lai*, MQ Shieh*, H Liu, Y Yang, E Hovy EMNLP 2017, 2017 | 1776 | 2017 |
| Meta pseudo labels H Pham, Z Dai, MQ Shieh, QV Le CVPR 2021, 2021 | 1053 | 2021 |
| Controllable invariance through adversarial feature learning MQ Shieh, Z Dai, Y Du, E Hovy, G Neubig NeurIPS 2017, 2017 | 350 | 2017 |
| Self-Evaluation Guided Beam Search for Reasoning Y Xie, K Kawaguchi, Y Zhao, JX Zhao, MY Kan, J He, MQ Xie NeurIPS 2023, 2023 | 295* | 2023 |
| Monte carlo tree search boosts reasoning via iterative preference learning Y Xie, A Goyal, W Zheng, MY Kan, TP Lillicrap, K Kawaguchi, M Shieh arXiv preprint arXiv:2405.00451, 2024 | 203 | 2024 |
| An interpretable knowledge transfer model for knowledge base completion Q Xie, X Ma, Z Dai, E Hovy ACL 2017, 2017 | 149 | 2017 |
| Large-scale cloze test dataset created by teachers Q Xie*, G Lai*, Z Dai, E Hovy EMNLP 2018, 2018 | 120* | 2018 |
| Simteg: A frustratingly simple approach improves textual graph learning K Duan, Q Liu, TS Chua, S Yan, WT Ooi, Q Xie, J He arXiv preprint arXiv:2308.02565, 2023 | 95 | 2023 |
| Automatic Model Selection with Large Language Models for Reasoning JX Zhao, Y Xie, K Kawaguchi, J He, MQ Xie EMNLP 2023 Findings, 2023 | 54 | 2023 |
| Codexgraph: Bridging large language models and code repositories via code graph databases X Liu*, B Lan*, Z Hu, Y Liu, Z Zhang, F Wang, M Shieh, W Zhou NAACL 2025, 2024 | 46 | 2024 |
| NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation X Liu*, J Ni*, Z Wu*, C Du, L Dou, H Wang, T Pang, MQ Shieh NeurIPS 2025, 2025 | 42 | 2025 |
| Accelerating greedy coordinate gradient and general prompt optimization via probe sampling Y Zhao, W Zheng, T Cai, K Kawaguchi, A Goyal, M Shieh NeurIPS 2024, 2024 | 38* | 2024 |
| Instructcoder: Instruction tuning large language models for code editing K Li*, Q Hu*, X Zhao, H Chen, Y Xie, T Liu, Q Xie, J He arXiv preprint arXiv:2310.20329, 2023 | 36* | 2023 |
| Prompt optimization via adversarial in-context learning XL Do*, Y Zhao*, H Brown*, Y Xie, JX Zhao, NF Chen, K Kawaguchi, ... ACL 2024, 2023 | 34 | 2023 |
| Understanding and enhancing safety mechanisms of LLMs via safety-specific neuron Y Zhao, W Zhang, Y Xie, A Goyal, K Kenji, MQ Shieh ICLR 2025, 2025 | 20* | 2025 |
| Can AI be as creative as humans? H Wang, J Zou, M Mozer, A Goyal, A Lamb, L Zhang, WJ Su, Z Deng, ... arXiv preprint arXiv:2401.01623, 2024 | 20 | 2024 |
| Self-evaluation as a defense against adversarial attacks on LLMs H Brown*, L Lin*, K Kawaguchi, M Shieh arXiv preprint arXiv:2407.03234, 2024 | 14 | 2024 |
| Recurrent polynomial network for dialogue state tracking K Sun, Q Xie, K Yu Dialogue & Discourse, 2015 | 13 | 2015 |
Eduard HovyUniversity of Melbourne, CMUVerified email at andrew.cmu.edu
