Sanath Kumar Krishnamurthy

Exponential Reward Weighting for Fine-Tuning Generative Recommenders under Sparse and Noisy Feedback

This work proposes Exponential reward-weighted fine-tuning (Exp-RSFT), where each logged interaction is weighted by $\exp(r/\lambda)$, and predicts performance follows an inverted-U trend as a function of $\lambda$, while PPO and DPO often over-optimize unreliable reward models and degrade recommendation quality.