SOURCE-LINKED INTELLIGENCE

Guiding the coarse levels of semantic IDs makes the fine levels learnable

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

Generative retrieval represents each item by a short Semantic ID and casts recommendation as autoregressive generation of that sequence. Because the tokenizer is trained independently to reconstruct an item embedding, its codes are aligned with neither the downstream LLM nor the end task. Nearly every SID system therefore spends extra effort to bridge this gap--alignment corpora, reasoning/RL, or per-token encoders to make codes legible, or learned tokenizer supervision to make them task-aware--yet the recovered meaning is content-derived and may not be the meaning the task needs. We introduce

Read original source ↗ Open in workspace

recordType

paper

region

Global