用 31B 开源模型进化搜索优化生成式检索的语义索引
Evolving Semantic Indexes for Generative Retrieval
用本地 31B 开源模型自动进化检索的语义索引设计，NQ320K 上 Recall@1 提到 59.3%，不用调 API，搞检索的可以看看。
论文提出用 LLM 驱动的进化程序搜索来优化生成式检索（GR）中的语义标识符（SID）设计，覆盖 SID 构建、碰撞处理、解码和训练四个环节。实验使用本地部署的 31B 开源模型变异可执行组件，不依赖专有 LLM API，并用 1M 参数的代理解码器替代反复训练 1B 目标生成器以加速反馈。在 NQ320K 上，代理与目标 Recall@100 的 Spearman 相关系数达 0.90；联合进化 SID 构建与碰撞处理后，Recall@1 从 55.8% 提升到 59.3%，Recall@100 从 85.8% 提升到 90.6%。该框架还在 MSMARCO300K 和一个多语言电商数据集上改善了种子 GR 的表现。
Evolving Semantic Indexes for Generative Retrieval
Generative retrieval (GR) casts search and recommendation as autoregressive generation of discrete semantic identifiers (SIDs). SID design largely determines GR quality, but its discrete, interdependent components (SID construction, collision handling, decoding, and training) cannot be optimized end-to-end with gradients and remain largely hand-designed. We introduce a framework that improves these components through LLM-driven evolutionary program search, to our knowledge the first application of this approach to GR. A locally served, open-weight 31B model mutates executable GR components, so no proprietary LLM API is used, and a 1M-parameter proxy decoder provides fast feedback in place of repeatedly training the 1B target generator. Across 21 SID programs on NQ320K, proxy and target Recall@100 show strong rank correlation (Spearman $ρ= 0.90$). Guided by this proxy, evolution improves the seed GR on NQ320K, MSMARCO300K, and a multilingual e-commerce dataset under a fixed training recipe. On NQ320K, jointly evolving SID construction and collision handling improves Recall@1 from 55.8% to 59.3% and Recall@100 from 85.8% to 90.6%. A component study shows that proxy reliability depends on what is evolved: improvements transfer reliably for the semantic index but not for the generator's training objective or the full pipeline. LLM-driven evolutionary search is thus a practical tool for GR design, provided proxy reliability is established for the chosen search space.