arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.14419cs.CLcs.LG
收藏

WavePhaseNet:一种基于离散傅里叶变换(DFT)的构建语义概念层次结构(SCHS)方法

WavePhaseNet: A DFT-Based Method for Constructing Semantic Conceptual Hierarchy Structures (SCHS)

Pionira Solutions LLC(皮奥尼拉解决方案有限公司)

Kiyotaka Kasubuchi, Kazuo Fukiya

AI总结:

WavePhaseNet通过DFT构建语义概念层次结构,利用频谱分析和上同调正则化实现语义一致性控制,减少维度以提升推理能力并抑制幻觉。

摘要:

本文通过测度论和频谱分析重新公式化大语言模型(LLMs)中的Transformer/注意力机制,理论上证明幻觉是结构限制的必然结果。嵌入空间作为σ-代数上的条件期望,其无法与语义真相集同构从根本上导致逻辑一致性破裂。WavePhaseNet方法作者提出WavePhaseNet,通过离散傅里叶变换(DFT)显式构建语义概念层次结构(SCHS)。通过在序列维度上应用DFT,将语义信息分解为频率带:低频成分捕捉全局意义和意图,高频成分代表局部语法和表达。这种分阶段分离使在对角化空间中实现精确的语义操作。维度缩减GPT-4的24576维嵌入空间基于语言自相似性和齐普夫定律表现出1/f频谱结构。通过累积能量分析,作者推导出约3000维构成“完整表示”的下限。这表明将24576维缩减到3000维在保持意义和意图的同时,使推理变得严谨并抑制幻觉。上同调一致性控制通过在重叠局部窗口上进行上同调正则化构建的缩减嵌入空间,允许定义图结构和上同调复形。这将局部推断之间的不一致量化为基于coboundary的损失。基于霍奇理论的谐波投影将上同调定位为可计算的正则化原理,用于控制语义一致性,提取最大一致的全局表示。

英文摘要:

This paper reformulates Transformer/Attention mechanisms in Large Language Models (LLMs) through measure theory and frequency analysis, theoretically demonstrating that hallucination is an inevitable structural limitation. The embedding space functions as a conditional expectation over a σ-algebra, and its failure to be isomorphic to the semantic truth set fundamentally causes logical consistency breakdown. WavePhaseNet Method The authors propose WavePhaseNet, which explicitly constructs a Semantic Conceptual Hierarchy Structure (SCHS) using Discrete Fourier Transform (DFT). By applying DFT along the sequence dimension, semantic information is decomposed into frequency bands: low-frequency components capture global meaning and intent, while high-frequency components represent local syntax and expression. This staged separation enables precise semantic manipulation in diagonalized space. Dimensionality Reduction GPT-4's 24,576-dimensional embedding space exhibits a 1/f spectral structure based on language self-similarity and Zipf's law. Through cumulative energy analysis, the authors derive that approximately 3,000 dimensions constitute the lower bound for "complete representation." This demonstrates that reduction from 24,576 to 3,000 dimensions preserves meaning and intent while enabling rigorous reasoning and suppressing hallucination. Cohomological Consistency Control The reduced embedding space, constructed via cohomological regularization over overlapping local windows, allows defining a graph structure and cochain complex. This quantifies inconsistencies among local inferences as coboundary-based losses. Applying harmonic projection based on Hodge theory positions cohomology as a computable regularization principle for controlling semantic consistency, extracting maximally consistent global representations.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑