Large language models (LLMs) are increasingly applied for tabular tasks using in-context learning. The prompt representation for a table may play a role in the LLMs ability to process the table. Inspired by prior work, we generate a collection of self-supervised structural tasks (e.g. navigate to a cell and row; transpose the table) and evaluate the performance differences when using 8 formats. In contrast to past work, we introduce 8 noise operations inspired by real-world messy data and adversarial inputs, and show that such operations can impact LLM performance across formats for different structural understanding tasks.
@article{arxiv.2310.10358,
title = {Tabular Representation, Noisy Operators, and Impacts on Table Structure Understanding Tasks in LLMs},
author = {Ananya Singha and José Cambronero and Sumit Gulwani and Vu Le and Chris Parnin},
journal= {arXiv preprint arXiv:2310.10358},
year = {2023}
}