EMNLP · 2025 · Conference paper · Top venue

VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs

Keer Lu, Keshi Zhao, Zhang, Zhuoran, Liang, Zheng, Da Pan, Shusen Zhang, X. Wu, Guosheng Dong, Bin Cui, Wang, Tengjiao, Wentao Zhang

PDF from arXiv.HTML · PDF · Open in a new tab ↗ · Close
Published in
Conference on Empirical Methods in Natural Language Processing
Date
2024-11-18
Citations
3
arXiv
2411.11266
Cite
@inproceedings{lu2025versatune,
  title = {VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs},
  author = {Keer Lu and Keshi Zhao and Zhang, Zhuoran and Liang, Zheng and Da Pan and Shusen Zhang and X. Wu and Guosheng Dong and Bin Cui and Wang, Tengjiao and Wentao Zhang},
  year = {2025},
  booktitle = {Conference on Empirical Methods in Natural Language Processing},
  eprint = {2411.11266},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2411.11266},
}