CoF-CoT：通过粗到细思维链提示增强大型语言模型以处理多领域 NLU 任务
CoF-CoT: Enhancing Large Language Models with Coarse-to-Fine Chain-of-Thought Prompting for Multi-domain NLU Tasks
AI总结：
针对思维链在大型语言模型自然语言理解任务中应用不足的问题，提出粗到细思维链方法，结合抽象意义表示结构化知识作为中间步骤，有效提升了模型在零样本和少样本多领域设置下处理多粒度NLU任务的能力。
摘要：
尽管思维链提示在推理任务中很流行，但其在大型语言模型（LLM）的自然语言理解（NLU）任务中的应用仍探索不足。受 LLM 多步推理启发，我们提出了粗到细思维链（CoF-CoT）方法，将 NLU 任务分解为多个推理步骤，使 LLM 能够学习获取并利用核心概念，从不同粒度解决任务。此外，我们提出利用基于语义的抽象意义表示（AMR）结构化知识作为中间步骤，以捕捉话语的细微差别与多样结构，并理解其不同粒度层级间的联系。实验表明，该方法能有效辅助 LLM 适应零样本和少样本多领域设置下的多粒度 NLU 任务。
英文摘要：
While Chain-of-Thought prompting is popular in reasoning tasks, its application to Large Language Models (LLMs) in Natural Language Understanding (NLU) is under-explored. Motivated by multi-step reasoning of LLMs, we propose Coarse-to-Fine Chain-of-Thought (CoF-CoT) approach that breaks down NLU tasks into multiple reasoning steps where LLMs can learn to acquire and leverage essential concepts to solve tasks from different granularities. Moreover, we propose leveraging semantic-based Abstract Meaning Representation (AMR) structured knowledge as an intermediate step to capture the nuances and diverse structures of utterances, and to understand connections between their varying levels of granularity. Our proposed approach is demonstrated effective in assisting the LLMs adapt to the multi-grained NLU tasks under both zero-shot and few-shot multi-domain settings.
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。
