Prompting for Numerical Sequences: A Case Study on Market Comment Generation

arXiv:2404.02466v1 Announce Type: new
Abstract: Large language models (LLMs) have been applied to a wide range of data-to-text generation tasks, including tables, graphs, and time-series numerical data-to-text settings. While research on generating prompts for structured data such as tables and graphs is gaining momentum, in-depth investigations into prompting for time-series numerical data are lacking. Therefore, this study explores various input representations, including sequences of tokens and structured formats such as HTML, LaTeX, and Python-style codes. In our experiments, we focus …

abstract arxiv case case study cs.ai cs.ce cs.cl data graphs investigations language language models large language large language models llms market numerical prompting prompts research series structured data study tables tasks text text generation type