# Glyph: A Multi-Strategy Agentic System for Column Description and Sensitivity-Ontology Tagging of Enterprise Data Catalogs

arXiv: https://arxiv.org/abs/2609.10430 · HTML: https://mlsanity.com/paper/2609.10430/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 20 of its 47 references that are in the map.
- First posted on arXiv 9 Sep 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [Efficient Natural Language Response Suggestion for Smart Reply](https://mlsanity.com/paper/1705.00652/) (2017)
- [TableLlama: Towards Open Large Generalist Models for Tables](https://mlsanity.com/paper/2311.09206/) (2023)
- [TABBIE: Pretrained Representations of Tabular Data](https://mlsanity.com/paper/2105.02584/) (2021)
- [Sherlock: A Deep Learning Approach to Semantic Data Type Detection](https://mlsanity.com/paper/1905.10688/) (2019)
- [GitTables: A Large-Scale Corpus of Relational Tables](https://mlsanity.com/paper/2106.07258/) (2021)
- [VizNet: Towards A Large-Scale Visualization Learning and Benchmarking Repository](https://mlsanity.com/paper/1905.04616/) (2019)
- [CHORUS: Foundation Models for Unified Data Discovery and Exploration](https://mlsanity.com/paper/2306.09610/) (2023)
- [RACOON: An LLM-based Framework for Retrieval-Augmented Column Type Annotation with a Knowledge Graph](https://mlsanity.com/paper/2409.14556/) (2024)

## Abstract (arXiv)

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 rightarrow 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.