APE: Active Learning-based Tooling for Finding Informative Few-shot Examples for LLM-based Entity Matching

TL;DR

This paper introduces APE, a human-in-the-loop active learning tool that efficiently identifies the most informative examples for prompt engineering in LLMs, reducing manual effort and improving task performance.

Contribution

The paper presents APE, a novel active learning-based tool that streamlines the selection of few-shot examples for LLM prompt engineering through iterative human feedback.

Findings

APE effectively identifies ambiguous examples for human review.

The tool reduces manual effort in selecting informative prompts.

Demonstration shows improved prompt quality with active learning.

Abstract

Prompt engineering is an iterative procedure often requiring extensive manual effort to formulate suitable instructions for effectively directing large language models (LLMs) in specific tasks. Incorporating few-shot examples is a vital and effective approach to providing LLMs with precise instructions, leading to improved LLM performance. Nonetheless, identifying the most informative demonstrations for LLMs is labor-intensive, frequently entailing sifting through an extensive search space. In this demonstration, we showcase a human-in-the-loop tool called APE (Active Prompt Engineering) designed for refining prompts through active learning. Drawing inspiration from active learning, APE iteratively selects the most ambiguous examples for human feedback, which will be transformed into few-shot examples within the prompt. The demo recording can be found with the submission or be viewed at https://youtu.be/OwQ6MQx53-Y.