arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2209.00455cs.LGcs.AI
收藏

让我来看看例子:通过显式模仿来增强演示学习

Let Me Check the Examples: Enhancing Demonstration Learning via Explicit Imitation

Meituan Inc.(美团公司)

Sirui Wang, Kaiwen Wei, Hongzhi Zhang, Yuntao Li, Wei Wu

摘要:

演示学习旨在通过在Few Shot设置中提供回答的演示来指导即时预测。尽管取得了可喜的成果,现有的工作只是连接回答的例子作为演示提示模板(包括原始上下文),没有任何额外的操作,忽略了演示的依赖关系。此外,先前的研究发现,随机替换演示的标签会对性能产生轻微影响,说明模型无法正确学习演示带来的知识。受人类学习过程的启发,本文引入模仿演示学习(Imitation-Demo),通过显式模仿人类的复习行为来强化演示学习,包括:(1)对比学习机制,集中于相似的演示。(2)演示-标签重新预测方法,以巩固已知的知识。实验结果表明,我们提出的方法达到了国家的最先进的性能上的11个14分类语料。进一步的研究也证明了模仿-演示强化了提示和演示之间的联系,这为探究演示学习的作用机制提供了依据。

英文摘要:

Demonstration learning aims to guide the prompt prediction via providing answered demonstrations in the few shot settings. Despite achieving promising results, existing work only concatenates the answered examples as demonstrations to the prompt template (including the raw context) without any additional operation, neglecting the prompt-demonstration dependencies. Besides, prior research found that randomly replacing the labels of demonstrations marginally hurts performance, illustrating that the model could not properly learn the knowledge brought by the demonstrations. Inspired by the human learning process, in this paper, we introduce Imitation DEMOnstration Learning (Imitation-Demo) to strengthen demonstration learning via explicitly imitating human review behaviour, which includes: (1) contrastive learning mechanism to concentrate on the similar demonstrations. (2) demonstration-label re-prediction method to consolidate known knowledge. Experiment results show that our proposed method achieves state-of-the-art performance on 11 out of 14 classification corpora. Further studies also prove that Imitation-Demo strengthen the association between prompt and demonstrations, which could provide the basis for exploring how demonstration learning works.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑