arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2207.10342cs.CLcs.AI
收藏

语言模型级联

Language Model Cascades

Google Research(谷歌研究院)
David Dohan, Winnie Xu, Aitor Lewkowycz, Jacob Austin, David Bieber, Raphael Gontijo Lopes, Yuhuai Wu, Henryk Michalewski, Rif A. Saurous, Jascha Sohl-dickstein… 展开作者

David Dohan, Winnie Xu, Aitor Lewkowycz, Jacob Austin, David Bieber, Raphael Gontijo Lopes, Yuhuai Wu, Henryk Michalewski, Rif A. Saurous, Jascha Sohl-dickstein, Kevin Murphy, Charles Sutton

摘要:

简化的模型已经展示了令人印象深刻的少样本学习能力。在测试时与单个模型或多个模型的组合进行重复交互,进一步扩展了功能。这些组合是概率模型,并且可以用具有随机变量的图形模型的语言来表达,随机变量的值是诸如字符串的复杂数据类型。控制流和动态结构的情况下,需要从概率编程技术,允许实现不同的模型结构和推理策略在一个统一的语言。我们从这个角度正式几个现有的技术,包括草稿/思维链,验证,STaR,选择推理,和工具使用。我们把产生的程序称为语言模型级联。

英文摘要:

Prompted models have demonstrated impressive few-shot learning abilities. Repeated interactions at test-time with a single model, or the composition of multiple models together, further expands capabilities. These compositions are probabilistic models, and may be expressed in the language of graphical models with random variables whose values are complex data types such as strings. Cases with control flow and dynamic structure require techniques from probabilistic programming, which allow implementing disparate model structures and inference strategies in a unified language. We formalize several existing techniques from this perspective, including scratchpads / chain of thought, verifiers, STaR, selection-inference, and tool use. We refer to the resulting programs as language model cascades.

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。

↑