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 Isolation Kernel Embedding or IKE, a learning-free method that transforms an LLM embedding into a binary embedding using Isolation Kernel (IK). Lightweight and based on binary encoding, IKE offers a 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 the original LLM embeddings, while maintaining comparable accuracy. Theoretically, we show that IKE works because it satisfies four essential criteria for effective binary hashing that other methods do not possess. Compared to CSR, IKE consistently achieves better retrieval efficiency and effectiveness. IKE also works effectively with graph-based indexing, demonstrating its superiority in balancing accuracy and latency compared to alternative compression techniques in the approximate nearest neighbor (ANN) search setting.

翻译：大型语言模型（LLMs）近期在文本表征领域取得了显著进展。然而，其嵌入向量通常维度较高，导致存储与检索开销显著。尽管马特廖什卡表征学习（MRL）和对比稀疏表征（CSR）等最新方法在一定程度上缓解了这些问题，但检索精度仍会下降。本文提出隔离核嵌入（IKE）方法，这是一种免学习的方法，利用隔离核（IK）将LLM嵌入向量转换为二值嵌入。基于二值编码的IKE具有轻量化特性，可实现低内存占用与快速位运算，从而降低检索延迟。在多个文本检索数据集上的实验表明，与原始LLM嵌入相比，IKE在保持相当精度的同时，可将检索速度提升16.7倍、内存占用降低16倍。理论层面，我们证明了IKE之所以有效，是因为它满足了其他方法不具备的有效二值哈希四项关键准则。与CSR相比，IKE在检索效率与有效性上均表现更优。此外，IKE还能与基于图的索引有效协同，在近似最近邻（ANN）搜索场景中展现出相较于其他压缩技术在精度与延迟平衡上的优越性。