# Robust LLM-based Column Type Annotation via Prompt Augmentation with LoRA Tuning

arXiv: https://arxiv.org/abs/2512.22742 · HTML: https://mlsanity.com/paper/2512.22742/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 33 references that are in the map.
- First posted on arXiv 28 Dec 2025.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs](https://mlsanity.com/paper/2410.12405/) (2024)
- [Sherlock: A Deep Learning Approach to Semantic Data Type Detection](https://mlsanity.com/paper/1905.10688/) (2019)
- [Black Box Adversarial Prompting for Foundation Models](https://mlsanity.com/paper/2302.04237/) (2023)
- [VizNet: Towards A Large-Scale Visualization Learning and Benchmarking Repository](https://mlsanity.com/paper/1905.04616/) (2019)
- [Mapping from Meaning: Addressing the Miscalibration of Prompt-Sensitive Language Models](https://mlsanity.com/paper/2510.17028/) (2025)
- [RACOON: An LLM-based Framework for Retrieval-Augmented Column Type Annotation with a Knowledge Graph](https://mlsanity.com/paper/2409.14556/) (2024)
- [Evaluating Knowledge Generation and Self-Refinement Strategies for LLM-based Column Type Annotation](https://mlsanity.com/paper/2503.02718/) (2025)

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

- [Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs](https://mlsanity.com/paper/2601.17058/) (2026)

## Abstract (arXiv)

Column Type Annotation (CTA) is a fundamental step towards enabling schema alignment and semantic understanding of tabular data. Existing encoder-only language models achieve high accuracy when fine-tuned on labeled columns, but their applicability is limited to in-domain settings, as distribution shifts in tables or label spaces require costly re-training from scratch. Recent work has explored prompting generative large language models (LLMs) by framing CTA as a multiple-choice task, but these approaches face two key challenges: (1) model performance is highly sensitive to subtle changes in prompt wording and structure, and (2) annotation F1 scores remain modest. A natural extension is to fine-tune large language models. However, fully fine-tuning these models incurs prohibitive computational costs due to their scale, and the sensitivity to prompts is not eliminated. In this paper, we present a parameter-efficient framework for CTA that trains models over prompt-augmented data via Low-Rank Adaptation (LoRA). Our approach mitigates sensitivity to prompt variations while drastically reducing the number of necessary trainable parameters, achieving robust performance across datasets and templates. Experimental results on recent benchmarks demonstrate that models fine-tuned with our prompt augmentation strategy maintain stable performance across diverse prompt patterns during inference and yield higher weighted F1 scores than those fine-tuned on a single prompt template. These results highlight the effectiveness of parameter-efficient training and augmentation strategies in developing practical and adaptable CTA systems.