arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.12246cs.CL
收藏

大型语言模型的主动提示与思维链

Active Prompting with Chain-of-Thought for Large Language Models

The Hong Kong University of Science and Technology(香港科技大学);University of Toronto(多伦多大学);The University of Hong Kong(香港大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

Shizhe Diao, Pengcheng Wang, Yong Lin, Rui Pan, Xiang Liu, Tong Zhang

AI总结:

本文提出Active-Prompt方法,通过不确定性度量选择最值得标注的问题,生成任务特定示例提示,结合思维链推理,使大型语言模型适应不同任务,在八个复杂推理任务上达到最先进水平。

摘要:

大型语言模型(LLMs)规模的不断扩大,为其带来了在各种需要推理的复杂任务(如算术和常识推理)中的涌现能力。众所周知,任务特定提示的有效设计对于LLMs生成高质量答案的能力至关重要。特别是,对于复杂的问答任务,一种有效的方法是使用基于示例的提示并结合思维链(CoT)推理,这显著提升了LLMs的性能。然而,当前的CoT方法依赖于一组固定的人工标注示例,这些示例不一定对不同任务都是最有效的。本文提出了一种新方法,即Active-Prompt,通过任务特定的示例提示(带有专家设计的CoT推理标注)来使LLMs适应不同任务。为此,我们针对一个关键问题提出了解决方案:如何从任务特定查询池中确定哪些问题是最重要且最值得标注的。通过借鉴基于不确定性的主动学习的相关思想,我们引入了多种度量标准来表征不确定性,从而选择最不确定的问题进行标注。实验结果表明,我们提出的方法具有优越性,在八个复杂推理任务上达到了最先进水平。对不同不确定性度量、池大小、零样本学习以及准确率-不确定性关系的进一步分析证明了我们方法的有效性。我们的代码将在https://github.com/shizhediao/active-prompt 上提供。

英文摘要:

The increasing scale of large language models (LLMs) brings emergent abilities to various complex tasks requiring reasoning, such as arithmetic and commonsense reasoning. It is known that the effective design of task-specific prompts is critical for LLMs' ability to produce high-quality answers. In particular, an effective approach for complex question-and-answer tasks is example-based prompting with chain-of-thought (CoT) reasoning, which significantly improves the performance of LLMs. However, current CoT methods rely on a fixed set of human-annotated exemplars, which are not necessarily the most effective examples for different tasks. This paper proposes a new method, Active-Prompt, to adapt LLMs to different tasks with task-specific example prompts (annotated with human-designed CoT reasoning). For this purpose, we propose a solution to the key problem of determining which questions are the most important and helpful ones to annotate from a pool of task-specific queries. By borrowing ideas from the related problem of uncertainty-based active learning, we introduce several metrics to characterize the uncertainty so as to select the most uncertain questions for annotation. Experimental results demonstrate the superiority of our proposed method, achieving state-of-the-art on eight complex reasoning tasks. Further analyses of different uncertainty metrics, pool sizes, zero-shot learning, and accuracy-uncertainty relationship demonstrate the effectiveness of our method. Our code will be available at https://github.com/shizhediao/active-prompt.

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。

↑