CDW-CoT: Clustered Distance-Weighted Chain-of-Thoughts Reasoning

2025-01-21

AI Summary

Existing chain-of-thought (CoT) prompting methods employ static, uniform prompts, lacking instance-level adaptability and thus exhibiting limited generalization on complex reasoning tasks. To address this, we propose a dynamic instance-adaptive CoT framework featuring the first clustering-driven, distance-weighted prompt probability modeling: K-means clustering is performed in the prompt embedding space, and a distance-aware probability distribution is learned to generate personalized CoT prompts for each input. The method is compatible with mainstream open-source LLMs—including LLaMA2 and LLaMA3—and achieves substantial improvements across six diverse reasoning benchmarks: average accuracy increases by 25.34% on LLaMA2-13B and 15.72% on LLaMA3-8B. These results empirically validate that instance-aware prompting significantly enhances reasoning robustness and cross-task transferability.

Technology Category

• Natural Language Processing: Prompt Engineering / Prompting
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Large Language Models (LLMs) have recently achieved impressive results in complex reasoning tasks through Chain of Thought (CoT) prompting. However, most existing CoT methods rely on using the same prompts, whether manually designed or automatically generated, to handle the entire dataset. This one-size-fits-all approach may fail to meet the specific needs arising from the diversities within a single dataset. To solve this problem, we propose the Clustered Distance-Weighted Chain of Thought (CDW-CoT) method, which dynamically constructs prompts tailored to the characteristics of each data instance by integrating clustering and prompt optimization techniques. Our method employs clustering algorithms to categorize the dataset into distinct groups, from which a candidate pool of prompts is selected to reflect the inherent diversity within the dataset. For each cluster, CDW-CoT trains the optimal prompt probability distribution tailored to their specific characteristics. Finally, it dynamically constructs a unique prompt probability distribution for each test instance, based on its proximity to cluster centers, from which prompts are selected for reasoning. CDW-CoT consistently outperforms traditional CoT methods across six datasets, including commonsense, symbolic, and mathematical reasoning tasks. Specifically, when compared to manual CoT, CDW-CoT achieves an average accuracy improvement of 25.34% on LLaMA2 (13B) and 15.72% on LLaMA3 (8B).

Problem

• Adaptability
• Problem-Solving Strategies
• Targeted Approach

Innovation

• Cluster Distance Weighting
• Chain of Thought
• Problem-Specific Strategy