Scholarlink

<p>P-tuning has demonstrated that anchor tokens are beneficial for improving the performance of downstream tasks. However, manual selection of anchor tokens may result in subjective or suboptimal results. In this paper, we present aCat to automatically select anchor tokens. Following the framework of the soft-hard prompt paradigm, aCat achieves automatic prompt template construction. Experiments conducted on natural language understanding benchmarks demonstrate the effectiveness of our proposed method. On the seven SuperGLUE datasets, aCat achieves higher accuracy than P-tuning, with an average accuracy surpassing P-tuning V2.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

aCat: Automatically Choosing Anchor Tokens in Prompt for Natural Language Understanding

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月10日

查看全文
  • Zhanhong Ye,
  • Leilei Kong,
  • Haoliang Qi

摘要

P-tuning has demonstrated that anchor tokens are beneficial for improving the performance of downstream tasks. However, manual selection of anchor tokens may result in subjective or suboptimal results. In this paper, we present aCat to automatically select anchor tokens. Following the framework of the soft-hard prompt paradigm, aCat achieves automatic prompt template construction. Experiments conducted on natural language understanding benchmarks demonstrate the effectiveness of our proposed method. On the seven SuperGLUE datasets, aCat achieves higher accuracy than P-tuning, with an average accuracy surpassing P-tuning V2.