Large language models (LLMs) have recently enabled remarkable progress in text representation. However, their embeddings are typically high-dimensional, leading to substantial storage and retrieval overhead. Although recent approaches such as Matryoshka Representation Learning (MRL) and Contrastive Sparse Representation (CSR) alleviate these issues to some extent, they still suffer from retrieval accuracy degradation. This paper proposes \emph{Isolation Kernel Embedding} or IKE, a learning-free method that transforms an LLM embedding into a binary embedding using Isolation Kernel (IK). IKE is an ensemble of diverse (random) partitions, enabling robust estimation of ideal kernel in the LLM embedding space, thus reducing retrieval accuracy loss as the ensemble grows. Lightweight and based on binary encoding, it offers low memory footprint and fast bitwise computation, lowering retrieval latency. Experiments on multiple text retrieval datasets demonstrate that IKE offers up to 16.7x faster retrieval and 16x lower memory usage than LLM embeddings, while maintaining comparable or better accuracy. Compared to CSR and other compression methods, IKE consistently achieves the best balance between retrieval efficiency and effectiveness.

翻译：大型语言模型（LLMs）近期在文本表示方面取得了显著进展。然而，其生成的嵌入向量通常具有高维度特性，导致显著的存储与检索开销。尽管近期提出的套娃表示学习（MRL）和对比稀疏表示（CSR）等方法在一定程度上缓解了这些问题，但它们仍存在检索精度下降的缺陷。本文提出一种免学习方法——隔离核嵌入（IKE），该方法利用隔离核（IK）将LLM嵌入向量转换为二进制嵌入。IKE通过集成多样化（随机）划分实现对LLM嵌入空间中理想核的稳健估计，随着集成规模的扩大，检索精度损失得以降低。该方法基于二进制编码实现轻量化，具有低内存占用和快速位运算的优势，从而显著降低检索延迟。在多个文本检索数据集上的实验表明：相较于原始LLM嵌入，IKE可实现最高16.7倍的检索加速和16倍的内存节省，同时保持相当或更优的检索精度。与CSR及其他压缩方法相比，IKE在检索效率与效果之间始终保持着最佳平衡。