Magneto: Combining Small and Large Language Models for Schema Matching

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Liu, Yurong, Pena, Eduardo, Santos, Aecio, Wu, Eden, Freire, Juliana
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909651066421248
author Liu, Yurong
Pena, Eduardo
Santos, Aecio
Wu, Eden
Freire, Juliana
author_facet Liu, Yurong
Pena, Eduardo
Santos, Aecio
Wu, Eden
Freire, Juliana
contents Recent advances in language models opened new opportunities to address complex schema matching tasks. Schema matching approaches have been proposed that demonstrate the usefulness of language models, but they have also uncovered important limitations: Small language models (SLMs) require training data (which can be both expensive and challenging to obtain), and large language models (LLMs) often incur high computational costs and must deal with constraints imposed by context windows. We present Magneto, a cost-effective and accurate solution for schema matching that combines the advantages of SLMs and LLMs to address their limitations. By structuring the schema matching pipeline in two phases, retrieval and reranking, Magneto can use computationally efficient SLM-based strategies to derive candidate matches which can then be reranked by LLMs, thus making it possible to reduce runtime without compromising matching accuracy. We propose a self-supervised approach to fine-tune SLMs which uses LLMs to generate syntactically diverse training data, and prompting strategies that are effective for reranking. We also introduce a new benchmark, developed in collaboration with domain experts, which includes real biomedical datasets and presents new challenges to schema matching methods. Through a detailed experimental evaluation, using both our new and existing benchmarks, we show that Magneto is scalable and attains high accuracy for datasets from different domains.
format Preprint
id arxiv_https___arxiv_org_abs_2412_08194
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Magneto: Combining Small and Large Language Models for Schema Matching
Liu, Yurong
Pena, Eduardo
Santos, Aecio
Wu, Eden
Freire, Juliana
Databases
Machine Learning
Recent advances in language models opened new opportunities to address complex schema matching tasks. Schema matching approaches have been proposed that demonstrate the usefulness of language models, but they have also uncovered important limitations: Small language models (SLMs) require training data (which can be both expensive and challenging to obtain), and large language models (LLMs) often incur high computational costs and must deal with constraints imposed by context windows. We present Magneto, a cost-effective and accurate solution for schema matching that combines the advantages of SLMs and LLMs to address their limitations. By structuring the schema matching pipeline in two phases, retrieval and reranking, Magneto can use computationally efficient SLM-based strategies to derive candidate matches which can then be reranked by LLMs, thus making it possible to reduce runtime without compromising matching accuracy. We propose a self-supervised approach to fine-tune SLMs which uses LLMs to generate syntactically diverse training data, and prompting strategies that are effective for reranking. We also introduce a new benchmark, developed in collaboration with domain experts, which includes real biomedical datasets and presents new challenges to schema matching methods. Through a detailed experimental evaluation, using both our new and existing benchmarks, we show that Magneto is scalable and attains high accuracy for datasets from different domains.
title Magneto: Combining Small and Large Language Models for Schema Matching
topic Databases
Machine Learning
url https://arxiv.org/abs/2412.08194