Help, Anna! Visual navigation with natural multimodal assistance via retrospective curiosity-encouraging imitation learning K Nguyen, H Daumé III EMNLP, 2019 | 145 | 2019 |
Posterior calibration and exploratory analysis for natural language processing models K Nguyen, B O'Connor EMNLP, 2015 | 129 | 2015 |
Vision-based navigation with language-based assistance via imitation learning with indirect intervention K Nguyen, D Dey, C Brockett, B Dolan CVPR, 2019 | 116 | 2019 |
Reinforcement learning for bandit neural machine translation with simulated human feedback K Nguyen, H Daumé III, J Boyd-Graber EMNLP, 2017 | 109 | 2017 |
Interactive learning from activity description K Nguyen, D Misra, R Schapire, M Dudík, P Shafto ICML, 2021 | 37 | 2021 |
Global Voices: Crossing borders in automatic news summarization K Nguyen, H Daumé III NEWSUMS workshop, EMNLP, 2019 | 32 | 2019 |
A framework for learning to request rich and contextually useful information from humans K Nguyen, Y Bisk, H Daumé III ICML, 16553-16568, 2022 | 10 | 2022 |
Imitation learning with recurrent neural networks K Nguyen arXiv preprint arXiv:1607.05241, 2016 | 9 | 2016 |
Define, evaluate, and improve task-oriented cognitive capabilities for instruction generation models L Zhao, K Nguyen, H Daumé III Findings of ACL, 2023 | 4 | 2023 |
The umd neural machine translation systems at wmt 2017 bandit learning task A Sharaf, S Feng, K Nguyen, K Brantley, H Daumé III WMT, 2017 | 4 | 2017 |
Hallucination detection for grounded instruction generation L Zhao, K Nguyen, H Daumé III EMNLP Findings, 2023 | 2 | 2023 |
The umd machine translation systems at iwslt 2015 A Axelrod, A Elgohary, M Martindale, K Nguyễn, X Niu, Y Vyas, M Carpuat IWSLT, 2015 | 2 | 2015 |
Language models are bounded pragmatic speakers: Understanding RLHF from a Bayesian cognitive modeling perspective K Nguyen | 1* | 2023 |
Successfully guiding humans with imperfect instructions by highlighting potential errors and suggesting corrections L Zhao, K Nguyen, H Daumé III arXiv preprint arXiv:2402.16973, 2024 | | 2024 |
Softmax probabilities (mostly) predict large language model correctness on multiple-choice Q&A B Plaut, K Nguyen, T Trinh arXiv preprint arXiv:2402.13213, 2024 | | 2024 |
Language-guided world models: A model-based approach to AI control A Zhang, K Nguyen, J Tuyls, A Lin, K Narasimhan arXiv preprint arXiv:2402.01695, 2024 | | 2024 |
Progressively efficient learning R Zheng, K Nguyen, H Daumé III, F Huang, K Narasimhan arXiv preprint arXiv:2310.13004, 2023 | | 2023 |
Enriching Communication Between Humans and AI Agents K Nguyen University of Maryland, College Park, 2022 | | 2022 |