2024/09/06 by Ziqi Jin, Z.-Z. Jin, Wei Lu +3 · 1 voice · 2 citations
Computer Science · #Computation and Language (cs.CL) #Constraint Satisfaction and Optimization #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Topic Modeling #cs.CL
paper · pdf · doi:10.48550/arxiv.2409.04057
openalex publication_date 2024/09/06 · arxiv published 2024/09/06 · arxiv updated 2025/02/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01
Chain-of-thought (CoT) prompting has demonstrated the capacity of large language models to perform complex reasoning through intermediate steps. While effective, current CoT methods face challenges: Zero-shot-CoT can lead to reasoning errors, and Few-shot-CoT requires labor-intensive manual demonstrations. Auto-CoT attempts to address these issues by automatically generating diverse demonstrations, but this diversity can lead to inconsistent reasoning patterns. We propose ECHO (Self-Harmonized Chain of Thought), a novel method that unifies diverse solution paths into a consistent and effective reasoning pattern. ECHO employs an iterative process to refine and harmonize automatically generated demonstrations, mitigating the limitations of existing approaches. Our comprehensive experiments across arithmetic, commonsense, and symbolic reasoning tasks demonstrate that ECHO outperforms Auto-CoT by an average of 2.8%. These findings suggest that ECHO represents a significant step towards more robust and generalizable automated reasoning in large language models.