GraphWiz: Instruction-Following LLM for Graph Problems
What it is
This repository provides the code, data, and models for GraphWiz, a series of instruction-tuned large language models designed to solve graph theory problems. It includes the GraphInstruct dataset, which contains over 72,500 training samples across nine graph tasks, enabling the models to map textual graph descriptions to explicit reasoning paths in natural language.
The problem it solves
Standard LLMs struggle with explicit graph reasoning and often fail to provide transparent reasoning paths for structural problems, limiting their reliability in graph-centric applications.
What you could use it for
- Solving graph theory problems like cycle detection and shortest path using natural language prompts
- Training custom LLMs for specific graph reasoning tasks using the provided GraphInstruct dataset
- Benchmarking LLM performance on complex graph structures against baselines like GPT-4 and Mistral
Read the source ↗Back to the library →
Summary written by an AI model from the source; check the source before you rely on it.