What Makes a Good Semantic ID for Generative Recommendation? A Reproducibility Study

2026-09-21

AI Summary

研究探讨了不同语义ID设计对生成式推荐的影响，通过大规模可复现性研究分析了代码本利用率、长度等因素，揭示了无单一最优设计。

Abstract

Generative recommendation has emerged as an active research direction, where items are commonly represented by semantic IDs (SIDs): discrete codes generated token by token. Despite strong empirical results, SID designs vary widely in construction strategy, codebook organization, and code length, making their true impact on recommendation performance unclear. We conduct a large-scale reproducibility study to systematically investigate the impact of semantic ID design on generative recommendation under a unified experimental framework. We focus on a fundamental question: What makes a good semantic ID for generative recommendation? To answer this question, we examine four aspects: the relative effectiveness of different semantic ID designs, the connection between codebook utilization and recommendation quality, the effect of semantic code length, and the influence of semantic ID design on local item semantic preservation. Through a unified evaluation and additional cross-dataset controlled analyses, we find that the effects of SID design are largely non-monotonic: no single SID design is universally best, and commonly used RQ-VAE- and OPQ-based designs can behave inconsistently across datasets. The method with the most balanced first-level codebook is not consistently the best recommender, showing that utilization is diagnostic but insufficient. Scaling either the generative backbone or the SID length is also not always beneficial. Finally, semantic-neighborhood analysis reveals that no single SID design dominates all notions of local semantic preservation; instead, different designs exhibit complementary strengths that remain stable across datasets and neighborhood sizes. Our study provides a controlled and reproducible understanding of semantic ID design and offers practical insights for future generative recommender systems.

Problem

• Semantic ID
• Generative Recommendation
• Codebook Organization
• Code Length
• Recommendation Performance

Innovation

• Semantic ID
• Generative Recommendation
• Reproducibility Study
• Codebook Utilization
• Local Semantic Preservation