Balancing Multiple Objectives in Generative Recommendations with Adaptive Decoding

TL;DR: We introduce Stochastic Primal-Dual Decoding (SPDD), a lightweight inference-time method that steers generative recommenders toward auxiliary objectives, without retraining. In a large-scale A/B test on playlist ranking, SPDD delivered +1.8 percentage points more auxiliary-objective gain than fixed-weight generation, with no loss in user consumption.

Source: https://research.atspotify.com/2026/8/balancing-multiple-objectives-in-generative-recommendations-with-adaptive-decoding. 8 Sync News only summarizes and links out; content copyright belongs to the authors and original sources.