发表机构
Meta（Meta）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对生成式检索中语义ID与任务不对齐的问题，提出Guided SID方法，通过监督索引分配强制粗粒度层级编码任务相关属性，在零额外成本下显著提升检索性能。
AI 中文摘要
生成式检索用短语义ID表示每个条目，并将推荐视为该序列的自回归生成。由于分词器是独立训练以重建条目嵌入的，其编码既不对齐下游大语言模型，也不对齐最终任务。因此，几乎每个SID系统都要花费额外精力来弥合这一差距——使用对齐语料、推理/强化学习、或逐词元编码器使编码可读，或使用学习到的分词器监督使其任务感知——但恢复出的意义源于内容，可能并非任务所需的意义。我们提出Guided SID，通过构造使最重要的层级具有意义：我们通过确定性监督索引分配（用属性标签覆盖最近邻选择）强制粗粒度RQ-VAE层级编码一个预定义的类别属性——该属性选择为基于文本（因此对大语言模型可读）且与任务相关——同时保持码本可学习（它们仍接收重建梯度）。一种trie合并构造将任何高基数或集合值属性映射到固定码预算上，同时保持合并桶语义连贯。引导本身不增加成本：尽管固定了粗粒度层级，碰撞和重建性能与普通基线相当或更优。在仅SID编码不同的匹配端到端A/B测试中，引导检索器在我们测量的每个列表长度上提升了recall@k（k=1时1.36倍，k=10时1.39倍），将平均倒数排名从0.0260提升到0.0355，并且预测预定义属性的频率提高了4.2倍。
英文摘要
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 Guided SID, which instead makes the levels that matter most meaningful by construction: we force the coarse RQ-VAE levels to encode a predefined categorical attribute--chosen to be text-grounded (hence legible to the LLM) and task-relevant--by deterministic supervised index assignment (overriding nearest-neighbor selection with the attribute label) while keeping the codebooks learnable (they still receive reconstruction gradients). A trie-merge construction maps any high-cardinality or set-valued attribute onto the fixed code budget while keeping merged buckets semantically coherent. Guiding costs nothing intrinsically: collision and reconstruction match or beat the vanilla baseline despite pinning the coarse level. In a matched end-to-end A/B differing only in the SID encoding, the guided retriever improves recall@k at every list length we measure (1.36x at k=1, 1.39x at k=10), raises mean reciprocal rank from 0.0260 to 0.0355, and predicts the pre-defined attribute 4.2x more often.
