Breaking Thought Patterns: A Multi-Dimensional Reasoning Framework for LLMs

TL;DR

This paper introduces LADDER, a multi-dimensional reasoning framework for LLMs that combines Chain-of-Thought, Mixture of Experts, and dimensionality strategies to enhance creativity, flexibility, and task performance.

Contribution

LADDER is a novel framework integrating CoT, MoE, and multi-dimensional strategies to improve reasoning and creative capabilities of large language models.

Findings

Significantly improves task completion and creativity.

Outperforms traditional models in coherence and fluency.

Ablation studies confirm the importance of CoT and MoE.

Abstract

Large language models (LLMs) are often constrained by rigid reasoning processes, limiting their ability to generate creative and diverse responses. To address this, a novel framework called LADDER is proposed, combining Chain-of-Thought (CoT) reasoning, Mixture of Experts (MoE) models, and multi-dimensional up/down-sampling strategies which breaks the limitations of traditional LLMs. First, CoT reasoning guides the model through multi-step logical reasoning, expanding the semantic space and breaking the rigidity of thought. Next, MoE distributes the reasoning tasks across multiple expert modules, each focusing on specific sub-tasks. Finally, dimensionality reduction maps the reasoning outputs back to a lower-dimensional semantic space, yielding more precise and creative responses. Extensive experiments across multiple tasks demonstrate that LADDER significantly improves task completion, creativity, and fluency, generating innovative and coherent responses that outperform traditional models. Ablation studies reveal the critical roles of CoT and MoE in enhancing reasoning abilities and creative output. This work contributes to the development of more flexible and creative LLMs, capable of addressing complex and novel tasks.