Papers by Chengming Shi
RewardDS: Privacy-Preserving Fine-Tuning for Large Language Models via Reward Driven Data Synthesis (2025.emnlp-main)
Copied to clipboard
Jianwei Wang, Chengming Shi, Junyao Yang, Haoran Li, Qianli Ma, Huiping Zhuang, Cen Chen, Ziqian Zeng
| Challenge: | Existing solutions to fine-tune large language models for domain-specific tasks are ineffective in addressing privacy concerns. |
| Approach: | They propose a privacy-preserving framework that fine-tunes a reward proxy model and uses reward signals to guide the synthetic data generation. |
| Outcome: | The proposed framework fine-tunes a reward proxy model and uses reward signals to guide the synthetic data generation. |