ChatGraph: Chat with Your Graphs
Yun Peng, Sen Lin, Qian Chen, Lyu Xu, Xiaojun Ren, Yafei Li, Jianliang Xu
TL;DR
ChatGraph tackles the difficulty of graph analysis via natural-language interactions by generating API chains for graph tasks. It introduces a three-module framework—API retrieval, graph-aware LLM, and API chain-oriented finetuning—along with a graph sequentializer and ANN-based API search to handle graph inputs. The authors demonstrate four real-world scenarios (understanding, comparison, cleaning, monitoring) on diverse graphs, showing improved usability and flexibility over SPARQL-like or drag-and-drop tools. This work broadens LLM-based data interaction to graphs, enabling domain experts to perform complex graph analyses without programming.
Abstract
Graph analysis is fundamental in real-world applications. Traditional approaches rely on SPARQL-like languages or clicking-and-dragging interfaces to interact with graph data. However, these methods either require users to possess high programming skills or support only a limited range of graph analysis functionalities. To address the limitations, we propose a large language model (LLM)-based framework called ChatGraph. With ChatGraph, users can interact with graphs through natural language, making it easier to use and more flexible than traditional approaches. The core of ChatGraph lies in generating chains of graph analysis APIs based on the understanding of the texts and graphs inputted in the user prompts. To achieve this, ChatGraph consists of three main modules: an API retrieval module that searches for relevant APIs, a graph-aware LLM module that enables the LLM to comprehend graphs, and an API chain-oriented finetuning module that guides the LLM in generating API chains.