zjukg/OntoTune-dpo-Llama3-8B

WWW2025. OntoTune: Ontology-Driven Self-training for Aligning Large Language Models

🔔 Introduction

1. This is the model parameter of OntoTune$_{dpo}$ fine-tuned based on Llama3 8B-Instruct.
2. This work was supported by Ant Group and Zhejiang University - Ant Group Joint Laboratory of Knowledge Graph

📖 Citation

Please consider citing this paper if you find our work useful.

@inproceedings{DBLP:conf/www/LiuGWZBSC025,
    title = {OntoTune: Ontology-Driven Self-training for Aligning Large Language Models},
    author = {Zhiqiang Liu and
                Chengtao Gan and
                Junjie Wang and
                Yichi Zhang and
                Zhongpu Bo and
                Mengshu Sun and
                Huajun Chen and
                Wen Zhang},
    editor = {Guodong Long and
                Michale Blumestein and
                Yi Chang and
                Liane Lewin{-}Eytan and
                Zi Helen Huang and
                Elad Yom{-}Tov},
    booktitle = {Proceedings of the {ACM} on Web Conference 2025, {WWW} 2025, Sydney, NSW, Australia, 28 April 2025- 2 May 2025},
    pages = {119--133},
    publisher = {{ACM}},
    year = {2025},
    url = {https://doi.org/10.1145/3696410.3714816},
    doi = {10.1145/3696410.3714816},
    timestamp = {Wed, 23 Apr 2025 16:35:50 +0200},
    biburl = {https://dblp.org/rec/conf/www/LiuGWZBSC025.bib},
    bibsource = {dblp computer science bibliography, https://dblp.org}
}