Prompt-tuning with Attribute Guidance for Low-resource Entity Matching

2026-03-16

AI Summary

This work addresses the limitations of existing entity matching methods in low-resource scenarios, where performance is constrained and interpretability is lacking due to the neglect of attribute-level information. The authors propose a prompt-tuning framework that jointly leverages entity-level and attribute-level soft prompts, introducing attribute-level prompts—used for the first time—to guide the matching process. By integrating fuzzy logic, the framework enables interpretable reasoning over matching decisions. Furthermore, inspired by SimCSE, it employs dropout-based contrastive learning to enhance the representation of prompts. Extensive experiments on multiple real-world datasets demonstrate that the proposed method significantly outperforms current low-resource entity matching approaches, achieving higher matching accuracy while providing greater interpretability in its predictions.

Technology Category

• Natural Language Processing: Prompt Engineering / Prompting
• Knowledge Representation and Reasoning: Preferences
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Entity Matching (EM) is an important task that determines the logical relationship between two entities, such as Same, Different, or Undecidable. Traditional EM approaches rely heavily on supervised learning, which requires large amounts of high-quality labeled data. This labeling process is both time-consuming and costly, limiting practical applicability. As a result, there is a strong need for low-resource EM methods that can perform well with minimal labeled data. Recent prompt-tuning approaches have shown promise for low-resource EM, but they mainly focus on entity-level matching and often overlook critical attribute-level information. In addition, these methods typically lack interpretability and explainability. To address these limitations, this paper introduces PROMPTATTRIB, a comprehensive solution that tackles EM through attribute-level prompt tuning and logical reasoning. PROMPTATTRIB uses both entity-level and attribute-level prompts to incorporate richer contextual information and employs fuzzy logic formulas to infer the final matching label. By explicitly considering attributes, the model gains a deeper understanding of the entities, resulting in more accurate matching. Furthermore, PROMPTATTRIB integrates dropout-based contrastive learning on soft prompts, inspired by SimCSE, which further boosts EM performance. Extensive experiments on real-world datasets demonstrate the effectiveness of PROMPTATTRIB.

Problem

• Entity Matching
• Low-resource
• Attribute-level Information
• Prompt-tuning
• Interpretability

Innovation

• prompt-tuning
• attribute-level matching
• fuzzy logic reasoning
• contrastive learning
• low-resource entity matching