wondergo2017/LLM4DyG
Implementation codes for KDD24 paper "LLM4DyG: Can Large Language Models Solve Spatial-Temporal Problems on Dynamic Graphs?"
This project helps evaluate how well Large Language Models (LLMs) can understand complex relationships that change over time and space, specifically within 'dynamic graphs' like social networks or transportation systems. It takes as input various LLMs and a set of nine defined spatial-temporal tasks on dynamic graph data. It then outputs performance metrics, showing how accurately the LLM handles these evolving network problems. Data scientists, machine learning researchers, and web data analysts focused on graph-based applications would find this useful.
No commits in the last 6 months.
Use this if you need to benchmark the performance of Large Language Models on problems involving evolving network structures and time-sensitive connections.
Not ideal if you are looking for a plug-and-play solution for a specific business problem, as this is a research framework for evaluating LLM capabilities.
Stars
33
Forks
3
Language
Python
License
—
Category
Last pushed
Sep 10, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/wondergo2017/LLM4DyG"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
RManLuo/reasoning-on-graphs
Official Implementation of ICLR 2024 paper: "Reasoning on Graphs: Faithful and Interpretable...
alibaba/GraphTranslator
GraphTranslator:Aligning Graph Model to Large Language Model for Open-ended Tasks
HKUDS/OpenGraph
[EMNLP'2024] "OpenGraph: Towards Open Graph Foundation Models"
HKUDS/GraphEdit
"GraphEdit: Large Language Models for Graph Structure Learning"
iMoonLab/LLM4Hypergraph
The source code of ICLR 2025 "Beyond Graphs: Can Large Language Models Comprehend Hypergraphs?"