Showing cs.CLShow all
2 papers · 1 filter
cs.CL2024
Learning from Contrastive Prompts: Automated Optimization and Adaptation
Mingqi Li, Karan Aggarwal, Yong Xie +2
As LLMs evolve, significant effort is spent on manually crafting prompts. While existing prompt optimization methods automate this process, they rely solely on learning from incorr…
cs.CL2024
Effectively Prompting Small-sized Language Models for Cross-lingual Tasks via Winning Tickets
Mingqi Li, Feng Luo
Current soft prompt methods yield limited performance when applied to small-sized models (fewer than a billion parameters). Deep prompt-tuning, which entails prepending parameters…