Backend
Keep it Simple! A Multiple-Choice Task can Benefit Generative Recommendation
arXiv cs.IR0 views
arXiv:2611.19320v2 Announce Type: replace Abstract: Sequential recommendation has recently witnessed growing interest in generative retrieval. One of the most popular approaches is to autoregressively generate the semantic identifiers (SIDs) of items as recommendations. Existing efforts mainly rely on semantic alignment, sophisticated architectural designs, and extensive hyperparameter tuning. However, the conventional learning framework for generative models could have foundational limitations. Specifically, most generative models directly predict target items without explicitly learning negative compositions and relative ranking signals. This is not well aligned with the philosophy of Bayesian personalized ranking (BPR), which emphasizes the importance of relative rankings between positive and negative samples. In this paper, we show that adding a simple multiple-choice auxiliary task into the learning objective can effectively address this issue. With minimal adaptation, we introduce Task Identifiers and Candidate Constructions to synthesize training data for the multiple-choice auxiliary task. In addition, we provide theoretical analysis of the fundamental benefits of the multiple-choice auxiliary task from the perspectives of information theory and compositional generalization. Extensive experiments on four publicly available benchmark datasets show that our approach can improve TIGER, a conventional generative recommendation model, by 4.9% to 79% in NDCG@10.
Source:https://arxiv.org/abs/2611.19320PreviousThe Missing Complement: State-Conditioned Minimal Sufficient Evidence for Coding AgentsNextMMIntentFlow: An Intent-Driven Real-Time Multimodal Search System with Image-Text Queries at Xiaohongshu
Related posts
Splunk's Empty Cluster Secret Turns a Standalone Default into an Authentication Bypass
0dev.to
Pragmatic zero-trust: what to ship in the first 90 days
0dev.to
The EKS cost playbook: 7 levers we pull on every audit
0dev.to
Building a hearing test in the browser with the Web Audio API (and why we refuse to call it an audiogram)
0dev.to
How we score French speaking with AI: an honest look at limits
0dev.to
What a Four-Letter Word Ladder Taught Me About Planning Under Constraints
0dev.to