Iterative Label Refinement Matters More than Preference Optimization under Weak Supervision

Yaowen Ye, Cassidy Laidlaw, Jacob Steinhardt. Iterative Label Refinement Matters More than Preference Optimization under Weak Supervision. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net, 2025. [doi]

Authors

Yaowen Ye

This author has not been identified. Look up 'Yaowen Ye' in Google

Cassidy Laidlaw

This author has not been identified. Look up 'Cassidy Laidlaw' in Google

Jacob Steinhardt

This author has not been identified. Look up 'Jacob Steinhardt' in Google