홈 › Papers

TACO: Task-Aware Column Description Generation Using LLMs

2026-06-19 · Ting Cai, Rakesh R. Menon, Yiru Chen, Zifan Liu, Yuan Tian, Fei Wu, Anudeep Chimakurthi, Prashanthi Ramamurthy, Sunav Choudhary, Kun Qian, Yunyao Li 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%.

📄 PDF Abstract BibTeX arXiv:2606.21685

Code (0)

등록된 구현이 없습니다.

Tasks

Question Answering Entity Linking

TACO: Ternary Absolute-max Column-wise One-sparse Optimizer for LLM Fine-Tuning

2026-10-01 · Jichao Jiang, Cristian McGee, El Houcine Bergou, Hanqin Cai 외 arxiv

Full-parameter fine-tuning of large language models (LLMs) incurs substantial optimizer state memory overhead, limiting the model sizes that fit on modern GPUs. Existing approaches either compress optimizer state, abando…

Computational Efficiency

Automatic database description generation for Text-to-SQL

2025-02-28 · Yingqi Gao, Zhiling Luo

In the context of the Text-to-SQL task, table and column descriptions are crucial for bridging the gap between natural language and database schema. This report proposes a method for automatically generating effective da…

Text to SQL Text-To-SQL

Adapting Like Humans: A Metacognitive Agent with Test-time Reasoning

2025-11-28 · Yang Li, Zhiyuan He, Yuxuan Huang, Zhuhanling Xiao 외 arxiv

Recent Vision-Language Models (VLMs) exhibit strong perceptual reasoning abilities, yet they often struggle to adapt efficiently when encountering novel tasks at test time. In contrast, humans leverage the metacognitive …

Reinforcement Learning Test-time Adaptation Atari Games

TACO: TActile World Model as a Self-COrrector forScalable VLA Post-Training

2026-07-03 · Shengbang Liu, Yueru Jia, Yuyang Yan, Jiaming Liu 외 arxiv

Vision-Language-Action (VLA) models have shown promising generalization in robotic manipulation, but they still struggle with contact-rich tasks, where minor contact perturbations can cause unrecoverable failures that ar…

Synthetic SQL Column Descriptions and Their Impact on Text-to-SQL Performance

2024-08-08 · Niklas Wretblad, Oskar Holmström, Erik Larsson, Axel Wiksäter 외

Relational databases often suffer from uninformative descriptors of table contents, such as ambiguous columns and hard-to-interpret values, impacting both human users and text-to-SQL models. In this paper, we explore the…