Learning to Ideate for Scientific Impact
This work constructs a large-scale dataset from over 100K computer science papers, and trains a goal-conditioned reward model to predict citation-impact labels from research goal and idea pairs, and uses this reward to align an idea generator through supervised fine-tuning followed by reinforcement learning.
Shubham Kale, Aniketh Garikaparthi, Manasi S. Patwardhan
· 0 citations