🪄 GraphWiz: An Instruction-Following Language Model for Graph Problems

Project Page: https://graph-wiz.github.io/

Paper: https://arxiv.org/abs/2402.16029.pdf

Code: https://github.com/nuochenpku/Graph-Reasoning-LLM

About Mathoctopus

This project aims at leveraging instruction-tuning to build a powerful instruction-following LLM that can map textural descriptions of graphs and structures, and then solve different graph problems explicitly in natural language.

• GraphWiz, a series of instruction-following LLMs that have strong graph problem-solving abilities and output explicit reasoning paths.
• GraphInstruct, which offers over 72.5k training samples across nine graph problem tasks, ranging in complexity from linear and polynomial to NP-complete, extending the scope, scale, and diversity of previous benchmarks.