- This is the code of the paper OntoTune: Ontology-Driven Self-training for Aligning Large Language Models (WWW2025).
In this work, we propose an ontology-driven self-training framework called OntoTune, which aims to align LLMs with ontology through in-context learning, enabling the generation of responses guided by the ontology.
2025-01OntoTune is accepted by WWW 2025 !2025-02Our paper is released on arxiv !
git clone https://github.com/zjukg/OntoTune.gitThe code of fine-tuning is constructed based on open-sourced repo LLaMA-Factory.
cd LLaMA-Factory
pip install -e ".[torch,metrics]"- The supervised instruction-tuned data generated by LLaMA3 8B for the LLM itself is placed in the link.
- Put the downloaded
OntoTune_sft.jsonfile underLLaMA-Factory/data/directory. - Evaluation datasets for hypernym discovery and medical question answering are in
LLaMA-Factory/data/evaluation_HDandLLaMA-Factory/data/evaluation_QA, respectively.
You need to add model_name_or_path parameter to yaml file。
cd LLaMA-Factory
llamafactory-cli train script/OntoTune_sft.yamlPlease consider citing this paper if you find our work useful.
@article{OntoTune,
title={OntoTune: Ontology-Driven Self-training for Aligning Large Language Models},
author={Liu, Zhiqiang and Gan, Chengtao and Wang, Junjie and Zhang, Yichi and Bo, Zhongpu and Sun, Mengshu and Chen, Huajun and Zhang, Wen},
journal={arXiv preprint arXiv:2502.05478},
year={2025}
}