Showing cs.CLShow all
2 papers · 1 filter
cs.CL2025
ORPP: Self-Optimizing Role-playing Prompts to Enhance Language Model Capabilities
Yifan Duan, Yihong Tang, Kehai Chen +2
High-quality prompts are crucial for eliciting outstanding performance from large language models (LLMs) on complex tasks. Existing research has explored model-driven strategies fo…
cs.CL2025
Efficient Safety Alignment of Large Language Models via Preference Re-ranking and Representation-based Reward Modeling
Qiyuan Deng, Xuefeng Bai, Kehai Chen +3
Reinforcement Learning (RL) algorithms for safety alignment of Large Language Models (LLMs), such as Direct Preference Optimization (DPO), encounter the challenge of distribution s…