# TACO: Task-Aware Column Description Generation Using LLMs

arXiv: https://arxiv.org/abs/2606.21685 · HTML: https://mlsanity.com/paper/2606.21685/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 57 references that are in the map.
- First posted on arXiv 19 Jun 2026.

## Builds on (most cited first, 23 of 23)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://mlsanity.com/paper/2305.03111/) (2023)
- [TAPAS: Weakly Supervised Table Parsing via Pre-training](https://mlsanity.com/paper/2004.02349/) (2020)
- [Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Survey](https://mlsanity.com/paper/2402.17944/) (2024)
- [TableFormer: Robust Transformer Modeling for Table-Text Encoding](https://mlsanity.com/paper/2203.00274/) (2022)
- [Sherlock: A Deep Learning Approach to Semantic Data Type Detection](https://mlsanity.com/paper/1905.10688/) (2019)
- [The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Models](https://mlsanity.com/paper/2408.07702/) (2024)
- [TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition](https://mlsanity.com/paper/2404.10150/) (2024)
- [Annotating Columns with Pre-trained Language Models](https://mlsanity.com/paper/2104.01785/) (2021)
- [MultiTabQA: Generating Tabular Answers for Multi-Table Question Answering](https://mlsanity.com/paper/2305.12820/) (2023)
- [Interactive Text-to-SQL Generation via Editable Step-by-Step Explanations](https://mlsanity.com/paper/2305.07372/) (2023)
- [Table-to-Text Generation with Effective Hierarchical Encoder on Three Dimensions (Row, Column and Time)](https://mlsanity.com/paper/1909.02304/) (2019)
- [NameGuess: Column Name Expansion for Tabular Data](https://mlsanity.com/paper/2310.13196/) (2023)
- [SQLucid: Grounding Natural Language Database Queries with Interactive Explanations](https://mlsanity.com/paper/2409.06178/) (2024)
- [TabGenie: A Toolkit for Table-to-Text Generation](https://mlsanity.com/paper/2302.14169/) (2023)
- [Synthetic SQL Column Descriptions and Their Impact on Text-to-SQL Performance](https://mlsanity.com/paper/2408.04691/) (2024)
- [Text-to-SQL Domain Adaptation via Human-LLM Collaborative Data Annotation](https://mlsanity.com/paper/2502.15980/) (2025)
- [Automatic database description generation for Text-to-SQL](https://mlsanity.com/paper/2502.20657/) (2025)
- [Columbo: Expanding Abbreviated Column Names for Tabular Data Using Large Language Models](https://mlsanity.com/paper/2508.09403/) (2025)
- [EvoSchema: Towards Text-to-SQL Robustness Against Schema Evolution](https://mlsanity.com/paper/2603.10697/) (2026)
- [Auto-Tag: Tagging-Data-By-Example in Data Lakes](https://mlsanity.com/paper/2112.06049/) (2021)
- [AdaTyper: Adaptive Semantic Column Type Detection](https://mlsanity.com/paper/2311.13806/) (2023)
- [Improving Table Understanding with LLMs and Entity-Oriented Search](https://mlsanity.com/paper/2508.17028/) (2025)

## Built on by (most cited first, 1 of 1)

- [Polaris: Learning to Generate Table Descriptions from Retrieval Feedback](https://mlsanity.com/paper/2608.17171/) (2026)

## Abstract (arXiv)

Generating accurate and informative column descriptions (e.g. "membership status of customers" for the column name "cust_mem") is essential for a wide range of downstream NLP tasks on tabular data, including NL2SQL, table question answering, and entity linking. This problem arises in enterprises, domain sciences, government data portals, and so on. Despite its importance, most real-world datasets suffer from missing or cryptic documentation, often due to abbreviated column names or domain-specific jargon. Existing approaches largely rely on single-prompt large language models (LLMs), which struggle with three key issues: (i) inconsistent or incorrect handling of abbreviations, (ii) hallucinated or incomplete descriptions, and (iii) redundancy or vagueness that hinders downstream performance. We present TACO, a task-aware framework for automatic column description generation using LLMs. TACO introduces a three-step pipeline: (1) abbreviation expansion, which standardizes column names; (2) description generation, which produces initial semantic descriptions enriched with synonyms and search-oriented keywords; and (3) description revision, which refines these outputs using simulated downstream tasks. In addition, we investigate human-in-the-loop extensions and release new evaluation datasets for entity linking and schema enrichment. Extensive experiments across public and proprietary datasets show that TACO consistently outperforms existing methods, improving downstream task performance by up to 32%.