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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tang, Xintong, Zhang, Meiru, Xiao, Shang, Jin, Junzhao, Zhao, Zihan, Li, Liwei, Zheng, Yang, Wu, Bangyi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913895645446144
author Tang, Xintong
Zhang, Meiru
Xiao, Shang
Jin, Junzhao
Zhao, Zihan
Li, Liwei
Zheng, Yang
Wu, Bangyi
author_facet Tang, Xintong
Zhang, Meiru
Xiao, Shang
Jin, Junzhao
Zhao, Zihan
Li, Liwei
Zheng, Yang
Wu, Bangyi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_13192
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Breaking Thought Patterns: A Multi-Dimensional Reasoning Framework for LLMs
Tang, Xintong
Zhang, Meiru
Xiao, Shang
Jin, Junzhao
Zhao, Zihan
Li, Liwei
Zheng, Yang
Wu, Bangyi
Computation and Language
Artificial Intelligence
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.
title Breaking Thought Patterns: A Multi-Dimensional Reasoning Framework for LLMs
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2506.13192