APAO: Adaptive Prefix-Aware Optimization for Generative Recommendation

2026-03-03

AI Summary

This work addresses a critical inconsistency in generative recommender systems, where training relies on ground-truth historical sequences while inference employs beam search—a mismatch that often leads to premature pruning of correct candidates due to low-scoring prefixes. To bridge this gap, the paper introduces prefix-level optimization and proposes the Adaptive Prefix-Aware (APA) framework. APA aligns the training objective with beam search inference by incorporating a novel prefix-level loss function and an adaptive worst-prefix selection mechanism that dynamically focuses on the most vulnerable prefixes during training. Theoretical analysis and extensive experiments across multiple datasets demonstrate that APA significantly enhances the performance of mainstream generative recommendation models, confirming its effectiveness and generalizability.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Natural Language Processing: Generation
• Data Mining & Knowledge Management: Recommender Systems

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

Generative recommendation has recently emerged as a promising paradigm in sequential recommendation. It formulates the task as an autoregressive generation process, predicting discrete tokens of the next item conditioned on user interaction histories. Existing generative recommendation models are typically trained with token-level likelihood objectives, such as cross-entropy loss, while employing multi-step beam search during inference to generate ranked item candidates. However, this leads to a fundamental training-inference inconsistency: standard training assumes ground-truth history is always available, ignoring the fact that beam search prunes low-probability branches during inference. Consequently, the correct item may be prematurely discarded simply because its initial tokens (prefixes) have low scores. To address this issue, we propose the Adaptive Prefix-Aware Optimization (APAO) framework, which introduces prefix-level optimization losses to better align the training objective with the inference setting. Furthermore, we design an adaptive worst-prefix optimization strategy that dynamically focuses on the most vulnerable prefixes during training, thereby enhancing the model's ability to retain correct candidates under beam search constraints. We provide theoretical analyses to demonstrate the effectiveness and efficiency of our framework. Extensive experiments on multiple datasets further show that APAO consistently alleviates the training-inference inconsistency and improves performance across various generative recommendation backbones. Our codes are publicly available at https://github.com/yuyq18/APAO.

Problem

• generative recommendation
• training-inference inconsistency
• beam search
• prefix-aware optimization
• sequential recommendation

Innovation

• generative recommendation
• training-inference inconsistency
• prefix-aware optimization
• adaptive worst-prefix optimization
• beam search