# Decoupled Residual Quantization for Robust Semantic IDs in Recommendation Source: [Decoupled Residual Quantization for Robust Semantic IDs in Recommendation]() Collection index: [llms.txt]() Data updated: 2026-06-02T05:03:19.763Z Authors: Xuesi Wang, Junjie Wang, Ziliang Wang, Weijie Bian, Guanxing Zhang Published: 2026-06-01T07:55:21.000Z ## Abstract Semantic IDs represent items as shared discrete token sequences and have become a practical tool for recommendation and retrieval. Yet it remains difficult to tell why a tokenizer fails: poor quality may come from codebook underutilization, unstable decision boundaries, or geometric distortion of the embedding space. This paper develops a quantitative framework for diagnosing these failures through expected codeword overlap and effective codebook capacity. The former measures expected codeword confusion under retrieval-time perturbation, while the latter converts that confusion into an effective number of usable, well-separated codes. The framework links semantic boundary confusion to both code usage imbalance and Euclidean geometric constraints. As a proof of concept, we present Decoupled Residual Quantization (DRQ), which separates continuous geometry reconstruction from discrete distribution matching. Experiments on a large-scale industrial dataset show that Semantic ID quality is multi-objective: symbolic robustness, reconstruction fidelity, and behavior-aware soft matching each stress different aspects of a tokenizer. These downstream observations are based on one proprietary industrial dataset, so they should be read as a case study rather than a universal benchmark claim. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Item-to-Item Retrieval on proprietary industrial short-video dataset](): Item-to-item retrieval; proprietary industrial short-video dataset; SID Embedding AUC: 91.21. - [Item-to-item retrieval on Proprietary industrial short-video dataset (Evaluation Pool)](): Item-to-item retrieval; Proprietary industrial short-video dataset (Evaluation Pool); Hit Rate Retention @20: 0.9999. ## Original sources and implementation [Original paper]() [PDF]()