mlsanityData to 14 Oct 2026

CoF-CoT: Enhancing Large Language Models with Coarse-to-Fine Chain-of-Thought Prompting for Multi-domain NLU Tasks

arXiv 2310.14623 ↗First posted 23 Oct 2023cs.CL cs.LGcited by 18

On the map: LLM reasoning → Prompting and chain-of-thought reasoning

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.

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.

Builds on

22 of 28 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework5 May
  2. 2022Complexity-Based Prompting for Multi-Step Reasoning3 Oct
  3. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Models21 May
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Models21 Mar

Other references · 18

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  3. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 318
  4. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  5. 2020SLURP: A Spoken Language Understanding Resource Packagecited by 198
  6. 2020MTOP: A Comprehensive Multilingual Task-Oriented Semantic Parsing Benchmarkcited by 158
  7. 2018Joint Slot Filling and Intent Detection via Capsule Neural Networkscited by 73
  8. 2018A Survey on Semantic Parsingcited by 62
  9. 2019SG-Net: Syntax-Guided Machine Reading Comprehensioncited by 52
  10. 2021Syntax-BERT: Improving Pre-trained Transformers with Syntax Treescited by 51
  11. 2020SlotRefine: A Fast Non-Autoregressive Model for Joint Intent Detection and Slot Fillingcited by 42
  12. 2020Syntax-Enhanced Pre-trained Modelcited by 30
6 more
  1. 2019Enhancing Machine Translation with Dependency-Aware Self-Attentioncited by 24
  2. 2020CG-BERT: Conditional Text Generation with BERT for Generalized Few-shot Intent Detectioncited by 23
  3. 2020Dynamic Semantic Matching and Aggregation Network for Few-shot Intent Detectioncited by 17
  4. 2023Enhancing Cross-lingual Transfer via Phonemic Transcription Integrationcited by 11
  5. 2023Slot Induction via Pre-trained Language Model Probing and Multi-level Contrastive Learningcited by 4
  6. 2022XQA-DST: Multi-Domain and Multi-Lingual Dialogue State Trackingcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 7; 2025: 7; 2026: 3.

18 papers.

Sort:

By area:

  1. 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systemscited by 170
  2. 2024Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoningcited by 110
  3. 2024Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontierscited by 51
  4. 2024TimeRefine: Temporal Grounding with Time Refining Video LLMcited by 15
  5. 2025What Makes a Good Natural Language Prompt?cited by 7
  6. 2024Prompting with Phonemes: Enhancing LLMs' Multilinguality for Non-Latin Script Languagescited by 6
  7. 2025Beyond In-Distribution Success: Scaling Curves of CoT Granularity for Language Model Generalizationcited by 5
  8. 2024CORI: CJKV Benchmark with Romanization Integration -- A step towards Cross-lingual Transfer Beyond Textual Scriptscited by 4
  9. 2025Semantic Mastery: Enhancing LLMs with Advanced Natural Language Understandingcited by 4
  10. 2023kNN-ICL: Compositional Task-Oriented Parsing Generalization with Nearest Neighbor In-Context Learningcited by 3
  11. 2025PFDial: A Structured Dialogue Instruction Fine-tuning Method Based on UML Flowchartscited by 3
  12. 2025Prompting is not Enough: Exploring Knowledge Integration and Controllable Generationcited by 2
6 more
  1. 2026Learning Transferable Topology Priors for Multi-Agent LLM Collaboration Across Domainscited by 2
  2. 2025From Large to Super-Tiny: End-to-End Optimization for Cost-Efficient LLMscited by 1
  3. 2024Traffic Light or Light Traffic? Investigating Phrasal Semantics in Large Language Modelscited by 0
  4. 2025SalaMAnder: Shapley-based Mathematical Expression Attribution and Metric for Chain-of-Thought Reasoningcited by 0
  5. 2026LLM-Driven Multi-Turn Task-Oriented Dialogue Synthesis for Realistic Reasoningcited by 0
  6. 2026Learning Generalizable Multimodal Representations for Software Vulnerability Detectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Chain-of-Thought Tuning: Masked Language Models can also Think Step By Step in Natural Language Understanding
  2. 2025Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning
  3. 2025CoT Vectors: Transferring and Probing the Reasoning Mechanisms of LLMs
  4. 2026Attention-guided Fine-tuning of Multimodal Large Language Models Improves Chain-of-Thought Reasoning
  5. 2024Enhancing Chain of Thought Prompting in Large Language Models via Reasoning Patterns
  6. 2023Semi-Structured Chain-of-Thought: Integrating Multiple Sources of Knowledge for Improved Language Model Reasoning
  7. 2025Advancing Reasoning in Large Language Models: Promising Methods and Approaches
  8. 2024Expediting and Elevating Large Language Model Reasoning via Hidden Chain-of-Thought Decoding