揭示数据分布如何塑造语言模型的嵌入结构
Probability Signature: Bridging Data Semantics and Embedding Structure in Language Models
- 用概率签名表征词元语义关系，解释嵌入结构成因
- 实验证明概率签名能精准预测嵌入中强成对相似性
- 适用于理解大模型嵌入组织机制，适合研究者参考
语言模型的嵌入空间被认为捕捉了语义关系；例如，数字词元的嵌入常呈现与其自然顺序一致的有序结构。然而，这种结构形成的机制仍不明确。本文通过数据分布解释嵌入结构，提出一组反映词元间语义关系的概率签名。在使用线性模型和前馈网络进行复合加法任务的实验中，结合梯度流动力学的理论分析，我们发现这些概率签名显著影响嵌入结构。进一步将分析推广至大语言模型，通过在Pile语料子集上训练Qwen2.5架构，结果表明概率签名与嵌入结构高度对齐，尤其在捕捉嵌入间的强成对相似性方面表现优异。本工作揭示了数据分布如何引导嵌入结构形成，建立了嵌入组织与语义模式之间新的理解。
原文摘要 · Abstract (English)
The embedding space of language models is widely believed to capture the semantic relationships; for instance, embeddings of digits often exhibit an ordered structure that corresponds to their natural sequence. However, the mechanisms driving the formation of such structures remain poorly understood. In this work, we interpret the embedding structures via the data distribution. We propose a set of probability signatures that reflect the semantic relationships among tokens. Through experiments on the composite addition tasks using the linear model and feedforward network, combined with theoretical analysis of gradient flow dynamics, we reveal that these probability signatures significantly influence the embedding structures. We further generalize our analysis to large language models (LLMs) by training the Qwen2.5 architecture on the subsets of the Pile corpus. Our results show that the probability signatures are faithfully aligned with the embedding structures, particularly in capturing strong pairwise similarities among embeddings. Our work uncovers the mechanism of how data distribution guides the formation of embedding structures, establishing a novel understanding of the relationship between embedding organization and semantic patterns.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。