CAC-CoT: Connector-Aware Compact Chain-of-Thought for Efficient Reasoning Data Synthesis Across Dual-System Cognitive Tasks

📅 2025-08-26
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
To address reasoning redundancy and efficiency degradation induced by chain-of-thought (CoT) prompting in “System 1” intuitive tasks, this paper proposes Connector-Aware Compact CoT (CAC-CoT). CAC-CoT introduces a connective-word constraint mechanism that retains only essential logical connectives (e.g., “therefore”, “because”) to generate structurally coherent, length-controllable compact reasoning chains. Unlike conventional free-form CoT generation, CAC-CoT constructs reasoning paths via fixed connective templates and leverages Gemini-2.0-Flash to synthesize high-quality training data. Experiments demonstrate that CAC-CoT achieves 85%, 40%, and 90% of the original performance on GSM8K, GPQA, and S1-Bench, respectively, while compressing average reasoning length to ~300 tokens and accelerating inference by 3×. This work marks the first approach enabling efficient joint modeling of System 1 (intuitive) and System 2 (analytic) reasoning tasks.

Technology Category

Application Category

📝 Abstract
Long chain-of-thought (CoT) prompting helps Large Language Models (LLMs) solve difficult problems, but very long traces often slow or even degrade performance on fast, intuitive "System-1" tasks. We introduce Connector-Aware Compact CoT (CAC-CoT) -- a method that deliberately restricts reasoning to a small, fixed set of connector phrases, steering the model toward concise and well -- structured explanations. Despite its simplicity, our synthetic method with Gemini-2.0-Flash yields a high-quality training quality. CAC-CoT achieves approximately 85% on GSM8K and approximately 40% on GPQA (System-2) while retaining approximately 90% on S1-Bench (System-1). Its reasoning traces average approximately 300 tokens(ART), about one-third the length of baseline traces, delivering higher efficiency without loss of accuracy.
Problem

Research questions and friction points this paper is trying to address.

Balancing reasoning efficiency with System-1 task performance
Reducing lengthy reasoning traces without accuracy loss
Synthesizing concise structured explanations for dual-system tasks
Innovation

Methods, ideas, or system contributions that make the work stand out.

Uses connector phrases to structure reasoning
Restricts reasoning to fixed concise explanations
Synthesizes efficient short reasoning traces
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
S
Sunguk Choi
DATUMO
Y
Yonghoon Kwon
DATUMO
H
Heondeuk Lee
DATUMO