paper-with-me

홈 › Papers

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

2023-10-23 · Hoang H. Nguyen, Ye Liu, Chenwei Zhang, Tao Zhang, Philip S. Yu

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.

📄 PDF Abstract BibTeX arXiv:2310.14623

Code (1)

nhhoang96/cof-cot 공식 구현

Tasks

Abstract Meaning RepresentationNatural Language Understanding

Similar Papers 제목 키워드 기반

GTPO and GRPO-S: Token and Sequence-Level Reward Shaping with Policy Entropy

2025-08-06 · Hongze Tan, Zihan Wang, Jianfei Pan, Jinghao Lin 외 arxiv

Reinforcement Learning (RL) is pivotal for enhancing Large Language Model (LLM) reasoning, yet mainstream algorithms such as GRPO and DAPO remain constrained by a coarse-grained credit assignment paradigm, where all toke…

Reinforcement Learning

Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation

2023-04-28 · Wenqing Zheng, S P Sharan, Ajay Kumar Jaiswal, Kevin Wang 외

For a complicated algorithm, its implementation by a human programmer usually starts with outlining a rough control flow followed by iterative enrichments, eventually yielding carefully generated syntactic structures and…

Code GenerationLanguage ModelingLanguage ModellingProgram Synthesis

CoFInAl: Enhancing Action Quality Assessment with Coarse-to-Fine Instruction Alignment

2024-04-22 · Kanglei Zhou, Junlin Li, Ruizhi Cai, Liyuan Wang 외

Action Quality Assessment (AQA) is pivotal for quantifying actions across domains like sports and medical care. Existing methods often rely on pre-trained backbones from large-scale action recognition datasets to boost p…

Action Quality AssessmentAction RecognitionLanguage ModelingLanguage Modelling+1

CFMS: A Coarse-to-Fine Multimodal Synthesis Framework for Enhanced Tabular Reasoning

2026-04-13 · Qixian Huang, Hongqiang Lin, Tong Fu, Yingsen Wang 외 arxiv

Reasoning over tabular data is a crucial capability for tasks like question answering and fact verification, as it requires models to comprehend both free-form questions and semi-structured tables. However, while methods…

Question AnsweringFact Verification

Audio-DeepThinker: Progressive Reasoning-Aware Reinforcement Learning for High-Quality Chain-of-Thought Emergence in Audio Language Models

2026-04-20 · Xiang He, Chenxing Li, Jinting Wang, Yan Rong 외 arxiv

Large Audio-Language Models (LALMs) have made significant progress in audio understanding, yet they primarily operate as perception-and-answer systems without explicit reasoning processes. Existing methods for enhancing …

Reinforcement Learning