ESRL: Efficient Sampling-based Reinforcement Learning for Sequence
GenerationAAAI Conference on Artificial Intelligence (AAAI), 2023 |
Preference-grounded Token-level Guidance for Language Model Fine-tuningNeural Information Processing Systems (NeurIPS), 2023 |
Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation
Practices for Generated TextJournal of Artificial Intelligence Research (JAIR), 2022 |
Learning Compact Metrics for MTConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 |
Doubly-Trained Adversarial Data Augmentation for Neural Machine
TranslationConference of the Association for Machine Translation in the Americas (AMTA), 2021 |
Convergence Properties of Stochastic HypergradientsInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2020 |