SyntheT2C: Generating Synthetic Data for Fine-Tuning Large Language Models on the Text2Cypher Task

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhong, Ziije, Zhong, Linqing, Sun, Zhaoze, Jin, Qingyun, Qin, Zengchang, Zhang, Xiaofan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912204800917504
author Zhong, Ziije
Zhong, Linqing
Sun, Zhaoze
Jin, Qingyun
Qin, Zengchang
Zhang, Xiaofan
author_facet Zhong, Ziije
Zhong, Linqing
Sun, Zhaoze
Jin, Qingyun
Qin, Zengchang
Zhang, Xiaofan
contents Integrating Large Language Models (LLMs) with existing Knowledge Graph (KG) databases presents a promising avenue for enhancing LLMs' efficacy and mitigating their "hallucinations". Given that most KGs reside in graph databases accessible solely through specialized query languages (e.g., Cypher), it is critical to connect LLMs with KG databases by automating the translation of natural language into Cypher queries (termed as "Text2Cypher" task). Prior efforts tried to bolster LLMs' proficiency in Cypher generation through Supervised Fine-Tuning (SFT). However, these explorations are hindered by the lack of annotated datasets of Query-Cypher pairs, resulting from the labor-intensive and domain-specific nature of such annotation. In this study, we propose SyntheT2C, a methodology for constructing a synthetic Query-Cypher pair dataset, comprising two distinct pipelines: (1) LLM-based prompting and (2) template-filling. SyntheT2C is applied to two medical KG databases, culminating in the creation of a synthetic dataset, MedT2C. Comprehensive experiments demonstrate that the MedT2C dataset effectively enhances the performance of backbone LLMs on Text2Cypher task via SFT. Both the SyntheT2C codebase and the MedT2C dataset are released in https://github.com/ZGChung/SyntheT2C.
format Preprint
id arxiv_https___arxiv_org_abs_2406_10710
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SyntheT2C: Generating Synthetic Data for Fine-Tuning Large Language Models on the Text2Cypher Task
Zhong, Ziije
Zhong, Linqing
Sun, Zhaoze
Jin, Qingyun
Qin, Zengchang
Zhang, Xiaofan
Artificial Intelligence
Computation and Language
Integrating Large Language Models (LLMs) with existing Knowledge Graph (KG) databases presents a promising avenue for enhancing LLMs' efficacy and mitigating their "hallucinations". Given that most KGs reside in graph databases accessible solely through specialized query languages (e.g., Cypher), it is critical to connect LLMs with KG databases by automating the translation of natural language into Cypher queries (termed as "Text2Cypher" task). Prior efforts tried to bolster LLMs' proficiency in Cypher generation through Supervised Fine-Tuning (SFT). However, these explorations are hindered by the lack of annotated datasets of Query-Cypher pairs, resulting from the labor-intensive and domain-specific nature of such annotation. In this study, we propose SyntheT2C, a methodology for constructing a synthetic Query-Cypher pair dataset, comprising two distinct pipelines: (1) LLM-based prompting and (2) template-filling. SyntheT2C is applied to two medical KG databases, culminating in the creation of a synthetic dataset, MedT2C. Comprehensive experiments demonstrate that the MedT2C dataset effectively enhances the performance of backbone LLMs on Text2Cypher task via SFT. Both the SyntheT2C codebase and the MedT2C dataset are released in https://github.com/ZGChung/SyntheT2C.
title SyntheT2C: Generating Synthetic Data for Fine-Tuning Large Language Models on the Text2Cypher Task
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2406.10710