一作ACL 2026Workshop· Natural Language Processing
CRL -Prompt: Contrastive and Reinforcement Learning for Soft Prompt Tuning for Text Classification
Danila Lapokin · Andrey V. Savchenko
摘要
Prompt choice is crucial in adapting language models to text classification tasks, particularly under low-resource conditions. Manual prompt engineering is time-consuming, non-scalable, and brittle, while current auto-prompting techniques are still far from maturity. This paper presents a two-sta...