Netflix develops Advantage-Weighted Supervised Fine-Tuning (A-SFT) to post-train generative recommender systems on noisy reward signals
Generative recommenders trained purely by imitating observed user behavior can perpetuate suboptimal recommendations because user interactions are influenced by trends and external suggestions. Standard post-training techniques developed for LLMs (PPO, DPO) cannot be directly applied to recommendation systems due to the absence of counterfactual data, noisy reward models, and unknown logging policies.
Reward models trained for recommendation settings do not significantly outperform simple baselines (average user reward or average title reward), because users explore only a small subset of titles and their viewing choices exhibit permutation invariance that makes reward learning difficult.
A-SFT achieves better alignment between the pre-trained generative recommendation model and the reward model, outperforming baseline behavior cloning as well as reward-model-dependent algorithms (CQL, PPO, DPO, IPO) on recommendation metrics including NDCG, HR, and MRR.
Frequently asked questions
What did this team achieve with this AI workflow?
A-SFT achieves better alignment between the pre-trained generative recommendation model and the reward model, outperforming baseline behavior cloning as well as reward-model-dependent algorithms (CQL, PPO, DPO, IPO) o…
What tools did this team use?
HSTU, PPO, DPO, GRPO, CQL, IPO.
What results were reported?
A-SFT improvement vs. baseline methods: largest improvement in metrics; Reward model vs. simple baselines: do not significantly outperform the simple baselines; Reward evaluation standard deviation: less than 4% (source-reported, not independently verified).
What failed first in this deployment?
Reward models trained for recommendation settings do not significantly outperform simple baselines (average user reward or average title reward), because users explore only a small subset of titles and their viewing c…
How is this workflow AI workflow structured?
User feedback signal collection → Reward model training → Advantage-weighted fine-tuning → Offline benchmark evaluation → Recommendation generation.