APrompt4EM: Augmented Prompt Tuning for Generalized Entity Matching

TL;DR

This paper presents APrompt4EM, an augmented prompt tuning framework for generalized entity matching that enhances low-resource record matching using soft token prompts and information augmentation with large language models, achieving high performance with low cost.

Contribution

The paper introduces a novel augmented prompt tuning framework with soft token prompts and LLM-based information augmentation for GEM, addressing prompt design and information gaps.

Findings

Improves GEM performance by 5.24%+ over existing methods.

Achieves comparable results to fine-tuned LLMs at less than 14% API cost.

Effective in low-resource GEM scenarios.

Abstract

Generalized Entity Matching (GEM), which aims at judging whether two records represented in different formats refer to the same real-world entity, is an essential task in data management. The prompt tuning paradigm for pre-trained language models (PLMs), including the recent PromptEM model, effectively addresses the challenges of low-resource GEM in practical applications, offering a robust solution when labeled data is scarce. However, existing prompt tuning models for GEM face the challenges of prompt design and information gap. This paper introduces an augmented prompt tuning framework for the challenges, which consists of two main improvements. The first is an augmented contextualized soft token-based prompt tuning method that extracts a guiding soft token benefit for the PLMs' prompt tuning, and the second is a cost-effective information augmentation strategy leveraging large language models (LLMs). Our approach performs well on the low-resource GEM challenges. Extensive experiments show promising advancements of our basic model without information augmentation over existing methods based on moderate-size PLMs (average 5.24%+), and our model with information augmentation achieves comparable performance compared with fine-tuned LLMs, using less than 14% of the API fee.