KARPA: A Training-free Method of Adapting Knowledge Graph as References for Large Language Model's Reasoning Path Aggregation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fang, Siyuan, Ma, Kaijing, Zheng, Tianyu, Du, Xinrun, Lu, Ningxuan, Zhang, Ge, Tang, Qingkun
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917881345736704
author Fang, Siyuan
Ma, Kaijing
Zheng, Tianyu
Du, Xinrun
Lu, Ningxuan
Zhang, Ge
Tang, Qingkun
author_facet Fang, Siyuan
Ma, Kaijing
Zheng, Tianyu
Du, Xinrun
Lu, Ningxuan
Zhang, Ge
Tang, Qingkun
contents Large language models (LLMs) demonstrate exceptional performance across a variety of tasks, yet they are often affected by hallucinations and the timeliness of knowledge. Leveraging knowledge graphs (KGs) as external knowledge sources has emerged as a viable solution, but existing methods for LLM-based knowledge graph question answering (KGQA) are often limited by step-by-step decision-making on KGs, restricting the global planning and reasoning capabilities of LLMs, or they require fine-tuning or pre-training on specific KGs. To address these challenges, we propose Knowledge graph Assisted Reasoning Path Aggregation (KARPA), a novel framework that harnesses the global planning abilities of LLMs for efficient and accurate KG reasoning. KARPA operates in three steps: pre-planning relation paths using the LLM's global planning capabilities, matching semantically relevant paths via an embedding model, and reasoning over these paths to generate answers. Unlike existing KGQA methods, KARPA avoids stepwise traversal, requires no additional training, and is adaptable to various LLM architectures. Extensive experimental results show that KARPA achieves state-of-the-art performance in KGQA tasks, delivering both high efficiency and accuracy. Our code will be available on Github.
format Preprint
id arxiv_https___arxiv_org_abs_2412_20995
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle KARPA: A Training-free Method of Adapting Knowledge Graph as References for Large Language Model's Reasoning Path Aggregation
Fang, Siyuan
Ma, Kaijing
Zheng, Tianyu
Du, Xinrun
Lu, Ningxuan
Zhang, Ge
Tang, Qingkun
Computation and Language
Artificial Intelligence
Large language models (LLMs) demonstrate exceptional performance across a variety of tasks, yet they are often affected by hallucinations and the timeliness of knowledge. Leveraging knowledge graphs (KGs) as external knowledge sources has emerged as a viable solution, but existing methods for LLM-based knowledge graph question answering (KGQA) are often limited by step-by-step decision-making on KGs, restricting the global planning and reasoning capabilities of LLMs, or they require fine-tuning or pre-training on specific KGs. To address these challenges, we propose Knowledge graph Assisted Reasoning Path Aggregation (KARPA), a novel framework that harnesses the global planning abilities of LLMs for efficient and accurate KG reasoning. KARPA operates in three steps: pre-planning relation paths using the LLM's global planning capabilities, matching semantically relevant paths via an embedding model, and reasoning over these paths to generate answers. Unlike existing KGQA methods, KARPA avoids stepwise traversal, requires no additional training, and is adaptable to various LLM architectures. Extensive experimental results show that KARPA achieves state-of-the-art performance in KGQA tasks, delivering both high efficiency and accuracy. Our code will be available on Github.
title KARPA: A Training-free Method of Adapting Knowledge Graph as References for Large Language Model's Reasoning Path Aggregation
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2412.20995