Showing cs.CLShow all
2 papers · 1 filter
cs.CL2024
PMoL: Parameter Efficient MoE for Preference Mixing of LLM Alignment
Dongxu Liu, Bing Xu, Yinzhuo Chen +4
Reinforcement Learning from Human Feedback (RLHF) has been proven to be an effective method for preference alignment of large language models (LLMs) and is widely used in the post-…
cs.CL2024
Self-Evaluation of Large Language Model based on Glass-box Features
Hui Huang, Yingqi Qu, Jing Liu +4
The proliferation of open-source Large Language Models (LLMs) underscores the pressing need for evaluation methods. Existing works primarily rely on external evaluators, focusing o…