CoF-CoT: Enhancing Large Language Models with Coarse-to-Fine Chain-of-Thought Prompting for Multi-domain NLU Tasks
Submission Type: Regular Short Paper
Submission Track: Dialogue and Interactive Systems
Submission Track 2: Theme Track: Large Language Models and the Future of NLP
Keywords: large language model, natural language understanding, chain-of-thought, multi-step reasoning, slot filling, intent detection, semantic parsing, abstract meaning representation
TL;DR: Proposal of Coarse-to-Fine-grained Chain-of-Thought prompting to solve multi-grained NLU tasks
Abstract: 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.
Submission Number: 2364
Loading