# Glyph：面向企业数据目录列描述与敏感本体标注的多策略智能体系统

- 来源：Apple Machine Learning Research（RSS）
- 发布时间：2026-09-16 08:00
- AIHOT 分数：35
- AIHOT 链接：https://aihot.news/items/cmu4j1u660sp4ro4wckrdun5u
- 原文链接：https://machinelearning.apple.com/research/glyph-column-description-tagging

## AI 摘要

Apple 提出生产系统 Glyph，用有状态图编排的 LLM 智能体同时完成列描述生成与列类型标注。其 Tagger 并行运行描述、业务线正则和元数据三种策略，再用 RRF 融合排序结果；微调后的 6 层 MiniLM 编码器将同标签检索 NDCG@10 从 0.55 提升至 0.92。系统基于 275 叶节点数据分类本体打标，并支持逐标签溯源与优雅降级。

## 正文

Enterprise data lakes accumulate tables faster than human stewards can document or classify them, leaving columns with missing descriptions and unassigned governance labels. This documentation debt undermines data discovery, access control, and regulatory compliance. We present Glyph, a production system that frames two coupled problems, column description generation and column type annotation for data classification, as cooperating LLM agents orchestrated as stateful graphs. The Descriptor grounds generation in the pipeline source code that produces each column, retrieved on demand from an enterprise GitHub via a reasoning–acting tool loop (active Retrieval-Augmented Generation).

The Tagger assigns labels from a governed 275-leaf Data Classification Ontology by running three complementary strategies in parallel (a description tagger, a line-of-business regex tagger, and a metadata tagger backed by a fine-tuned contrastive encoder over a vector database), then fuses their ranked outputs with Reciprocal Rank Fusion (RRF). We fine-tune a 6-layer MiniLM metadata encoder with an in-batch contrastive objective, lifting same-tag retrieval on an in-distribution held-out split from NDCG@10 0.55 to 0.92 (MAP@100 0.19→ 0.90) relative to the stock base encoder.

We report end-to-end multi-label tagging quality under a recall-weighted F2 objective across three evaluation groups, an ablation isolating each strategy and the RRF fusion, and the engineering decisions that distinguish Glyph from prior column-type-annotation work and from commercial value/regex sensitivity scanners: value-free and code-grounded design, per-tag provenance, and graceful degradation. Together these make multi-agent LLM cataloging auditable and operable as a production service.