# Leveraging Retrieval Augmented Generative LLMs For Automated Metadata Description Generation to Enhance Data Catalogs

arXiv: https://arxiv.org/abs/2503.09003 · HTML: https://mlsanity.com/paper/2503.09003/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation.
- Builds on 8 of its 32 references that are in the map.
- First posted on arXiv 12 Mar 2025.

## Placed in

- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)

## Builds on (most cited first, 8 of 8)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [The Faiss library](https://mlsanity.com/paper/2401.08281/) (2024)
- [AlignScore: Evaluating Factual Consistency with a Unified Alignment Function](https://mlsanity.com/paper/2305.16739/) (2023)
- [Column Type Annotation using ChatGPT](https://mlsanity.com/paper/2306.00745/) (2023)

## Built on by (most cited first, 3 of 3)

- [PIPER: Content-Based Table Search via profiling and LLM-Generated Pseudoqueries](https://mlsanity.com/paper/2605.18199/) (2026)
- [A GitOps-Driven Annotation Catalog for Fully Automatic Railway Operations](https://mlsanity.com/paper/2608.04724/) (2026)
- [Polaris: Learning to Generate Table Descriptions from Retrieval Feedback](https://mlsanity.com/paper/2608.17171/) (2026)

## Abstract (arXiv)

Data catalogs serve as repositories for organizing and accessing diverse collection of data assets, but their effectiveness hinges on the ease with which business users can look-up relevant content. Unfortunately, many data catalogs within organizations suffer from limited searchability due to inadequate metadata like asset descriptions. Hence, there is a need of content generation solution to enrich and curate metadata in a scalable way. This paper explores the challenges associated with metadata creation and proposes a unique prompt enrichment idea of leveraging existing metadata content using retrieval based few-shot technique tied with generative large language models (LLM). The literature also considers finetuning an LLM on existing content and studies the behavior of few-shot pretrained LLM (Llama, GPT3.5) vis-`a-vis few-shot finetuned LLM (Llama2-7b) by evaluating their performance based on accuracy, factual grounding, and toxicity. Our preliminary results exhibit more than 80% Rouge-1 F1 for the generated content. This implied 87%- 88% of instances accepted as is or curated with minor edits by data stewards. By automatically generating descriptions for tables and columns in most accurate way, the research attempts to provide an overall framework for enterprises to effectively scale metadata curation and enrich its data catalog thereby vastly improving the data catalog searchability and overall usability.