ChatGraph: Chat with Your Graphs
This addresses the problem of accessibility for users who need to analyze graphs but lack programming expertise, though it appears incremental as it builds on existing LLM and API technologies.
The authors tackled the problem of making graph analysis more accessible by proposing ChatGraph, a framework that allows users to interact with graphs using natural language instead of requiring programming skills or limited interfaces, resulting in a system that is easier to use and more flexible than traditional methods.
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.