# CoF-CoT: Enhancing Large Language Models with Coarse-to-Fine Chain-of-Thought Prompting for Multi-domain NLU Tasks arXiv: https://arxiv.org/abs/2310.14623 ยท HTML: https://mlsanity.com/paper/2310.14623/ ## Key facts - Cited by 18 papers in the map (data through 14 Oct 2026). - Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. - Builds on 22 of its 28 references that are in the map. - First posted on arXiv 23 Oct 2023. ## Placed in - LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/) ## Builds on (most cited first, 22 of 22) - [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022) - [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022) - [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022) - [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022) - [Complexity-Based Prompting for Multi-Step Reasoning](https://mlsanity.com/paper/2210.00720/) (2022) - [Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP](https://mlsanity.com/paper/2212.14024/) (2022) - [UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models](https://mlsanity.com/paper/2201.05966/) (2022) - [SLURP: A Spoken Language Understanding Resource Package](https://mlsanity.com/paper/2011.13205/) (2020) - [MTOP: A Comprehensive Multilingual Task-Oriented Semantic Parsing Benchmark](https://mlsanity.com/paper/2008.09335/) (2020) - [Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework](https://mlsanity.com/paper/2305.03268/) (2023) - [Joint Slot Filling and Intent Detection via Capsule Neural Networks](https://mlsanity.com/paper/1812.09471/) (2018) - [A Survey on Semantic Parsing](https://mlsanity.com/paper/1812.00978/) (2018) - [SG-Net: Syntax-Guided Machine Reading Comprehension](https://mlsanity.com/paper/1908.05147/) (2019) - [Syntax-BERT: Improving Pre-trained Transformers with Syntax Trees](https://mlsanity.com/paper/2103.04350/) (2021) - [SlotRefine: A Fast Non-Autoregressive Model for Joint Intent Detection and Slot Filling](https://mlsanity.com/paper/2010.02693/) (2020) - [Syntax-Enhanced Pre-trained Model](https://mlsanity.com/paper/2012.14116/) (2020) - [Enhancing Machine Translation with Dependency-Aware Self-Attention](https://mlsanity.com/paper/1909.03149/) (2019) - [CG-BERT: Conditional Text Generation with BERT for Generalized Few-shot Intent Detection](https://mlsanity.com/paper/2004.01881/) (2020) - [Dynamic Semantic Matching and Aggregation Network for Few-shot Intent Detection](https://mlsanity.com/paper/2010.02481/) (2020) - [Enhancing Cross-lingual Transfer via Phonemic Transcription Integration](https://mlsanity.com/paper/2307.04361/) (2023) - [Slot Induction via Pre-trained Language Model Probing and Multi-level Contrastive Learning](https://mlsanity.com/paper/2308.04712/) (2023) - [XQA-DST: Multi-Domain and Multi-Lingual Dialogue State Tracking](https://mlsanity.com/paper/2204.05895/) (2022) ## Built on by (most cited first, 18 of 18) - [A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems](https://mlsanity.com/paper/2402.18013/) (2024) - [Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning](https://mlsanity.com/paper/2412.09078/) (2024) - [Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers](https://mlsanity.com/paper/2404.04925/) (2024) - [TimeRefine: Temporal Grounding with Time Refining Video LLM](https://mlsanity.com/paper/2412.09601/) (2024) - [What Makes a Good Natural Language Prompt?](https://mlsanity.com/paper/2506.06950/) (2025) - [Prompting with Phonemes: Enhancing LLMs' Multilinguality for Non-Latin Script Languages](https://mlsanity.com/paper/2411.02398/) (2024) - [Beyond In-Distribution Success: Scaling Curves of CoT Granularity for Language Model Generalization](https://mlsanity.com/paper/2502.18273/) (2025) - [CORI: CJKV Benchmark with Romanization Integration -- A step towards Cross-lingual Transfer Beyond Textual Scripts](https://mlsanity.com/paper/2404.12618/) (2024) - [Semantic Mastery: Enhancing LLMs with Advanced Natural Language Understanding](https://mlsanity.com/paper/2504.00409/) (2025) - [kNN-ICL: Compositional Task-Oriented Parsing Generalization with Nearest Neighbor In-Context Learning](https://mlsanity.com/paper/2312.10771/) (2023) - [PFDial: A Structured Dialogue Instruction Fine-tuning Method Based on UML Flowcharts](https://mlsanity.com/paper/2503.06706/) (2025) - [Prompting is not Enough: Exploring Knowledge Integration and Controllable Generation](https://mlsanity.com/paper/2505.19660/) (2025) - [Learning Transferable Topology Priors for Multi-Agent LLM Collaboration Across Domains](https://mlsanity.com/paper/2605.17359/) (2026) - [From Large to Super-Tiny: End-to-End Optimization for Cost-Efficient LLMs](https://mlsanity.com/paper/2504.13471/) (2025) - [Traffic Light or Light Traffic? Investigating Phrasal Semantics in Large Language Models](https://mlsanity.com/paper/2410.02308/) (2024) - [SalaMAnder: Shapley-based Mathematical Expression Attribution and Metric for Chain-of-Thought Reasoning](https://mlsanity.com/paper/2509.16561/) (2025) - [LLM-Driven Multi-Turn Task-Oriented Dialogue Synthesis for Realistic Reasoning](https://mlsanity.com/paper/2602.23610/) (2026) - [Learning Generalizable Multimodal Representations for Software Vulnerability Detection](https://mlsanity.com/paper/2604.25711/) (2026) ## Abstract (arXiv) 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.