CoF-CoT: Enhancing Large Language Models with Coarse-to-Fine Chain-of-Thought Prompting for Multi-domain NLU Tasks
This addresses improving LLM performance on multi-grained NLU tasks, but appears incremental as it builds on existing Chain-of-Thought methods.
The paper tackles the under-exploration of Chain-of-Thought prompting for Large Language Models in Natural Language Understanding by proposing Coarse-to-Fine Chain-of-Thought, which breaks tasks into reasoning steps and uses Abstract Meaning Representation to capture nuances, showing effectiveness in multi-domain settings.
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.