Apple's Glyph lifts column-description retrieval NDCG@10 to 0.92
Apple self-reports its production system Glyph uses collaborative LLM agents to auto-generate column descriptions and sensitivity tags, raising retrieval NDCG@10 from 0.55 to 0.92.
ImportanceLocalEvidenceE2 unreplicated
Column description generation and sensitivity tagging for enterprise data catalogs can now be done automatically by collaborative LLM agents: Apple self-reports that after fine-tuning a 6-layer MiniLM, same-tag retrieval NDCG@10 on an internal held-out set rose from 0.55 to 0.92.
Previously this work relied on manual effort, costly and hard to scale; Glyph's description agent retrieves the pipeline source code that generates the column on demand, and the tagging agent runs three strategies in parallel over a 275-leaf classification ontology, fused with RRF.
The measurement comes from an Apple Machine Learning Research blog post published September 16, with the paper submitted to arXiv on September 9.
What it does not cover and who has not yet reproduced it are not stated in the original.