1 citations · 3 across the 4 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.CL2023★ 1 cited
Enabling Language Models to Implicitly Learn Self-Improvement
Ziqi Wang, Le Hou, Tianjian Lu +4
Large Language Models (LLMs) have demonstrated remarkable capabilities in open-ended text generation tasks. However, the inherent open-ended nature of these tasks implies that ther…
cs.CL2023★ 1 cited
Parameter-Efficient Tuning Helps Language Model Alignment
Tianci Xue, Ziqi Wang, Heng Ji
Aligning large language models (LLMs) with human preferences is essential for safe and useful LLMs. Previous works mainly adopt reinforcement learning (RLHF) and direct preference…