@article{diversityasarewardfinetuningllmsona, title = {Diversity as a Reward: Fine-Tuning LLMs on a Mixture of Domain-Undetermined Data}, author = {Zhenqing Ling and Daoyuan Chen and Liuyi Yao and Yaliang Li and Ying Shen}, year = {2025}, eprint = {2502.04380}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.04380v1}, }