An Automatic Prompt Generation System for Tabular Data Tasks

TL;DR

This paper introduces an automatic prompt generation system for tabular data tasks that leverages reinforcement learning and similarity-based methods to improve LLM performance across multiple datasets and tasks.

Contribution

It presents a novel auto-prompt generation system with minimal training, specifically designed for tabular data, using reinforcement learning and similarity-based techniques.

Findings

Improved performance on data imputation, error detection, and entity matching

Effective across 66 datasets and multiple LLMs

Demonstrates the system's versatility and robustness

Abstract

Efficient processing of tabular data is important in various industries, especially when working with datasets containing a large number of columns. Large language models (LLMs) have demonstrated their ability on several tasks through carefully crafted prompts. However, creating effective prompts for tabular datasets is challenging due to the structured nature of the data and the need to manage numerous columns. This paper presents an innovative auto-prompt generation system suitable for multiple LLMs, with minimal training. It proposes two novel methods; 1) A Reinforcement Learning-based algorithm for identifying and sequencing task-relevant columns 2) Cell-level similarity-based approach for enhancing few-shot example selection. Our approach has been extensively tested across 66 datasets, demonstrating improved performance in three downstream tasks: data imputation, error detection, and entity matching using two distinct LLMs; Google flan-t5-xxl and Mixtral 8x7B.