RiTeK: A Dataset for Large Language Models Complex Reasoning over Textual Knowledge Graphs in Medicine

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Huang, Jiatan, Li, Mingchen, Yao, Zonghai, Li, Dawei, Zhang, Yuxin, Yang, Zhichao, Xiao, Yongkang, Ouyang, Feiyun, Li, Xiaohan, Han, Shuo, Yu, Hong
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911585385054208
author Huang, Jiatan
Li, Mingchen
Yao, Zonghai
Li, Dawei
Zhang, Yuxin
Yang, Zhichao
Xiao, Yongkang
Ouyang, Feiyun
Li, Xiaohan
Han, Shuo
Yu, Hong
author_facet Huang, Jiatan
Li, Mingchen
Yao, Zonghai
Li, Dawei
Zhang, Yuxin
Yang, Zhichao
Xiao, Yongkang
Ouyang, Feiyun
Li, Xiaohan
Han, Shuo
Yu, Hong
contents Answering complex real-world questions in the medical domain often requires accurate retrieval from medical Textual Knowledge Graphs (medical TKGs), as the relational path information from TKGs could enhance the inference ability of Large Language Models (LLMs). However, the main bottlenecks lie in the scarcity of existing medical TKGs, the limited expressiveness of their topological structures, and the lack of comprehensive evaluations of current retrievers for medical TKGs. To address these challenges, we first develop a Dataset1 for LLMs Complex Reasoning over medical Textual Knowledge Graphs (RiTeK), covering a broad range of topological structures. Specifically, we synthesize realistic user queries integrating diverse topological structures, relational information, and complex textual descriptions. We conduct a rigorous medical expert evaluation process to assess and validate the quality of our synthesized queries. RiTeK also serves as a comprehensive benchmark dataset for evaluating the capabilities of retrieval systems built upon LLMs. By assessing 11 representative retrievers on this benchmark, we observe that existing methods struggle to perform well, revealing notable limitations in current LLM-driven retrieval approaches. These findings highlight the pressing need for more effective retrieval systems tailored for semi-structured data in the medical domain.
format Preprint
id arxiv_https___arxiv_org_abs_2410_13987
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle RiTeK: A Dataset for Large Language Models Complex Reasoning over Textual Knowledge Graphs in Medicine
Huang, Jiatan
Li, Mingchen
Yao, Zonghai
Li, Dawei
Zhang, Yuxin
Yang, Zhichao
Xiao, Yongkang
Ouyang, Feiyun
Li, Xiaohan
Han, Shuo
Yu, Hong
Computation and Language
Answering complex real-world questions in the medical domain often requires accurate retrieval from medical Textual Knowledge Graphs (medical TKGs), as the relational path information from TKGs could enhance the inference ability of Large Language Models (LLMs). However, the main bottlenecks lie in the scarcity of existing medical TKGs, the limited expressiveness of their topological structures, and the lack of comprehensive evaluations of current retrievers for medical TKGs. To address these challenges, we first develop a Dataset1 for LLMs Complex Reasoning over medical Textual Knowledge Graphs (RiTeK), covering a broad range of topological structures. Specifically, we synthesize realistic user queries integrating diverse topological structures, relational information, and complex textual descriptions. We conduct a rigorous medical expert evaluation process to assess and validate the quality of our synthesized queries. RiTeK also serves as a comprehensive benchmark dataset for evaluating the capabilities of retrieval systems built upon LLMs. By assessing 11 representative retrievers on this benchmark, we observe that existing methods struggle to perform well, revealing notable limitations in current LLM-driven retrieval approaches. These findings highlight the pressing need for more effective retrieval systems tailored for semi-structured data in the medical domain.
title RiTeK: A Dataset for Large Language Models Complex Reasoning over Textual Knowledge Graphs in Medicine
topic Computation and Language
url https://arxiv.org/abs/2410.13987