GraphGen

github.com/open-sciencelab/graphgen
Active1Kupdated 1 month ago
Python
Apache-2.0

Knowledge graph-guided synthetic data generation for LLM fine-tuning, achieving strong performance on scientific QA (GPQA-Diamond) and math reasoning (AIME)

Sourced from

  • Awesome AI for Sciencegithub.com/open-sciencelab/graphgen
  • GitHubgithub.com/open-sciencelab/graphgen

Related resources

Comprehensive collection of papers on unifying LLMs and knowledge graphs

Idle2.6K1 year ago

Incremental knowledge graph construction using LLMs with entity extraction and Neo4j visualization

Active9512 months ago
Python
Apache-2.0

Generalized biological foundation model with unified nucleic acid and protein language, integrating DNA/RNA/protein sequences (Nature Machine Intelligence 2025)

Active3651 month ago
Python
Apache-2.0

Structure-aware prefix adaptation for integrating LLMs with knowledge graphs (ACM MM 2024)

Idle2121 year ago
Python
MIT

## Introduction (简介) This model is a domain-specific expert fine-tuned from Qwen/Qwen2.5-7B-Instruct using LoRA (Low-Rank Adaptation). It is specifically designed for Fine-grained Information Extraction (IE) of technical indicator quintuples from highly complex lithium-ion battery patents.

Active102 months ago
Python

Advanced OCR with PP-StructureV3 document parsing, 13% accuracy improvement, supports 80+ languages

Active81.3K1 month ago
Python
Apache-2.0