High-quality text embedding is pivotal in improving semantic textual similarity (STS) tasks, which are crucial components in Large Language Model (LLM) applications. However, a common challenge existing text embedding models face is the problem of vanishing gradients, primarily due to their reliance on the cosine function in the optimization objective, which has saturation zones. To address this issue, this paper proposes a novel angle-optimized text embedding model called AnglE. The core idea of AnglE is to introduce angle optimization in a complex space. This novel approach effectively mitigates the adverse effects of the saturation zone in the cosine function, which can impede gradient and hinder optimization processes. To set up a comprehensive STS evaluation, we experimented on existing short-text STS datasets and a newly collected long-text STS dataset from GitHub Issues. Furthermore, we examine domain-specific STS scenarios with limited labeled data and explore how AnglE works with LLM-annotated data. Extensive experiments were conducted on various tasks including short-text STS, long-text STS, and domain-specific STS tasks. The results show that AnglE outperforms the state-of-the-art (SOTA) STS models that ignore the cosine saturation zone. These findings demonstrate the ability of AnglE to generate high-quality text embeddings and the usefulness of angle optimization in STS.

翻译：高质量文本嵌入对于提升语义文本相似度（STS）任务至关重要，而该任务是大型语言模型（LLM）应用中的核心组成部分。然而，现有文本嵌入模型普遍面临梯度消失问题，这主要源于其优化目标依赖余弦函数——该函数存在饱和区域。针对这一问题，本文提出一种名为AnglE的新型角度优化文本嵌入模型。其核心思想是在复数空间中引入角度优化，这一创新方法有效缓解了余弦函数饱和区域阻碍梯度传播、干扰优化过程的负面影响。为构建全面的STS评估体系，我们在现有短文本STS数据集和从GitHub Issues新收集的长文本STS数据集上进行了实验。此外，我们还考察了标注数据受限的领域特定STS场景，并探索了AnglE与LLM标注数据的协作机制。通过涵盖短文本STS、长文本STS及领域特定STS的多项任务大规模实验，结果表明：AnglE显著优于忽视余弦饱和区域的最先进（SOTA）STS模型。这些发现验证了AnglE生成高质量文本嵌入的能力，以及角度优化在STS任务中的实用价值。