A Unified Taxonomy-Guided Instruction Tuning Framework for Entity Set Expansion and Taxonomy Expansion

TL;DR

This paper introduces a unified instruction tuning framework that enables large language models to perform entity set expansion, taxonomy expansion, and seed-guided taxonomy construction by teaching them to find siblings and parents, improving performance across tasks.

Contribution

The paper presents a novel taxonomy-guided instruction tuning framework that generalizes across three related tasks, leveraging shared skills for better performance.

Findings

Outperforms task-specific baselines on multiple benchmarks

Effectively teaches LLMs to find siblings and parents for entities

Demonstrates the benefits of joint pre-training for related tasks

Abstract

Entity set expansion, taxonomy expansion, and seed-guided taxonomy construction are three representative tasks that can be applied to automatically populate an existing taxonomy with emerging concepts. Previous studies view them as three separate tasks. Therefore, their proposed techniques usually work for one specific task only, lacking generalizability and a holistic perspective. In this paper, we aim at a unified solution to the three tasks. To be specific, we identify two common skills needed for entity set expansion, taxonomy expansion, and seed-guided taxonomy construction: finding "siblings" and finding "parents". We propose a taxonomy-guided instruction tuning framework to teach a large language model to generate siblings and parents for query entities, where the joint pre-training process facilitates the mutual enhancement of the two skills. Extensive experiments on multiple benchmark datasets demonstrate the efficacy of our proposed TaxoInstruct framework, which outperforms task-specific baselines across all three tasks.