An Automatic Prompt Generation System for Tabular Data Tasks
This addresses the problem of inefficient prompt engineering for tabular data processing in industries, offering a novel but incremental solution.
The paper tackled the challenge of creating effective prompts for tabular data tasks by developing an automatic prompt generation system, which improved performance in data imputation, error detection, and entity matching across 66 datasets using LLMs like Google flan-t5-xxl and Mixtral 8x7B.
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.