混合任务场景下基于大型语言模型的可泛化思维链提示
Generalizable Chain-of-Thought Prompting in Mixed-task Scenarios with Large Language Models
AI总结：
本文提出GeM-CoT方法，通过先分类问题类型再从对应数据池自动采样或构建演示，在混合任务场景中同时提升思维链提示的泛化能力与推理性能，并在10个公共推理任务和23个BBH任务上验证了有效性。
摘要：
大型语言模型（LLMs）通过利用思维链（CoT）提示展现了卓越的推理能力，该提示生成中间推理链作为推导答案的依据。然而，当前的CoT方法要么简单地使用诸如“让我们逐步思考”之类的通用提示，要么严重依赖预定义的特定任务演示来获得更优性能，从而在性能与泛化性之间产生了不可避免的差距。为了弥合这一差距，我们提出了GeM-CoT，一种在输入问题类型未知的混合任务场景中可泛化的CoT提示机制。GeM-CoT首先对问题类型进行分类，随后以自动模式从相应的数据池中采样或构建演示。凭借这一技术设计，GeM-CoT在10个公共推理任务和23个BBH任务上同时具备优越的泛化能力和出色的性能。
英文摘要：
Large language models (LLMs) have unveiled remarkable reasoning capabilities by exploiting chain-of-thought (CoT) prompting, which generates intermediate reasoning chains to serve as the rationale for deriving the answer. However, current CoT methods either simply employ general prompts such as Let's think step by step, or heavily rely on pre-defined task-specific demonstrations to attain preferable performances, thereby engendering an inescapable gap between performance and generalization. To bridge this gap, we propose GeM-CoT, a Generalizable CoT prompting mechanism in Mixed-task scenarios where the type of input questions is unknown. GeM-CoT first categorizes the question type and subsequently samples or constructs demonstrations from the corresponding data pool in an automatic pattern. With this technical design, GeM-CoT simultaneously enjoys superior generalization capabilities and remarkable performances on 10 public reasoning tasks and 23 BBH tasks.
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。
