Prompting in the Dark: Assessing Human Performance in Prompt Engineering for Data Labeling When Gold Labels Are AbsentInternational Conference on Human Factors in Computing Systems (CHI), 2025 |
ORIS: Online Active Learning Using Reinforcement Learning-based
Inclusive Sampling for Robust Streaming Analytics SystemBigData Congress [Services Society] (BSS), 2024 |
Linear Alignment: A Closed-form Solution for Aligning Human Preferences
without Tuning and FeedbackInternational Conference on Machine Learning (ICML), 2024 |
Conditions on Preference Relations that Guarantee the Existence of
Optimal PoliciesInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2023 |
Compositional preference models for aligning LMsInternational Conference on Learning Representations (ICLR), 2023 |