cs.CLNov 4, 2026

Balancing hierarchical representation and quantization: A performance trade-off in text embeddings

Authors: Kai Ponel, Marco Polignano, Erasmo Purificato, Aylin Julia Temizkan, Marco Levantesi, Giovanni Semeraro, Ernesto William De Luca

Organizations: Ludwig-Maximilian-University Munich, Geschwister-Scholl-Platz 1, Munich, Germany · Otto von Guericke University Magdeburg, Universitätsplatz 2, Magdeburg, Germany · University of Bari Aldo Moro, Via E. Orabona 4, Bari, Apulia, Italy · European Commission, Joint Research Centre (JRC), Via E. Fermi 2749, Ispra, Italy · 

Abstract

Hierarchical text embedding models offer variable-length representations, while quantization reduces numerical precision; both aim to improve computational efficiency. This work is an empirical benchmark study of how these two orthogonal, already-established techniques interact. We evaluate 38 tasks from the Massive Text Embedding Benchmark (MTEB) using four transformer-based embedding models, covering 1D and 2D hierarchical representations combined with 32-bit, 8-bit, and binary quantization, for 168 configurations per task. We report each efficiency dimension separately: theoretical per-vector storage and end-to-end evaluation time. Under a Friedman test with Nemenyi post-hoc analysis, int8 quantization is statistically indistinguishable from float32 for pair classification and re-ranking and costs at most 1.5 percentage points overall, whereas binary quantization is significantly worse across every task category. Halving the embedding dimension once is not statistically detectable above m=16m=16; two successive halvings always are. Combining an 8x dimensionality reduction with int8 yields a 32x reduction in per-vector storage at 94.4% of baseline effectiveness. Because evaluation times were measured once, we treat them as indicative: we find no evidence that quantization speeds up evaluation, whereas sampling from intermediate layers shortens it substantially. Retrieval degrades far faster than every other category, so we report findings per task category.

Figures & tables

Explore similar work

May 31, 2026

When Is 0.1% Enough? Analyzing the Combined Effects of Dimensionality Reduction and Quantization on Text Embedding Compression

Recent high-performing text embedding models often produce high-dimensional real-valued vectors, resulting in substantial storage and computational costs. To address this issue, embedding compression methods based on dimensionality reduction or quantization have been proposed; however, the effects of their combination have not been sufficiently investigated. In this paper, we systematically investigate how dimensionality reduction and quantization jointly affect embedding compression across four task families in the Massive Text Embedding Benchmark (MTEB), using five pretrained embedding models. Our results show that combining dimensionality reduction and quantization can preserve near-original performance with substantially smaller storage footprints than either method alone. In particular, for classification, several models retain at least 99% of their original classification score using less than 0.1% of the storage required by the original embeddings. The preferred balance between dimensionality and bit-width varies across tasks, with retrieval generally being more sensitive to compression.
Sep 14, 2026

Where Post-Training Quantization Breaks Text Embedders: A Measured Map Across Four Embedder Families

Weight-only post-training quantization is the cheapest way to shrink a retrieval embedder, and the received advice for applying it -- protect the embedding table, allocate bits by module sensitivity, prefer a ranking-aware objective over weight reconstruction -- was carried into LLM quantization largely intact. We test that advice on retrieval embedders directly, quantizing five checkpoints from four architecture families across a grid of bit widths and group sizes, and isolating the embedding, attention and feed-forward blocks at each width. Every heuristic fails to transfer as stated. The embedding table never emerges as the dominant isolated protection priority in any family, despite being the largest tensor in several of them. Module sensitivity does not survive as a transferable ordering: at INT4/g16 the spread between modules is too small to allocate against, at INT3 the ordering becomes family-dependent and joint damage stops being the sum of its parts, and at INT2 comparable reconstruction error accompanies retention ranging from 1.3 to 65.9 percent of full precision. A cheap reconstruction proxy is useful for screening uniform bit widths but substantially less reliable for choosing which tensors to protect; its apparent strength across the whole grid is a range-extension artifact. A distilled 109M student at INT3 holds 78.04 NDCG@10 in 68.4 MB and dominates the extreme-PTQ arm of its own 0.6B teacher, 297.9 MB at 64.46, on both size and quality -- but only inside the task it was distilled for. Sizes are byte counts of files that exist rather than arithmetic estimates, and the measurement repository carries the byte provenance for every one of them.
Jun 24, 2026

BitNet Text Embeddings

LLM-based text embedders have substantially improved retrieval and semantic representation quality, but their deployment remains costly: large backbone models slow down embedding inference, while high-dimensional full-precision embeddings impose substantial storage and bandwidth overhead on large-scale indexes. In this paper, we present BITEMBED, an extreme low-bit framework for LLM-based text embedding that jointly targets encoding efficiency and vector storage. BITEMBED converts pretrained LLM backbones into BitNet-style embedding encoders with ternary weights, quantized activations, and lightweight normalization refinement. The converted model is adapted to representation learning through continual contrastive pre-training, followed by supervised contrastive fine-tuning with both similarity-distribution distillation and attention-relation distillation from a full-precision teacher. Beyond quantizing the backbone, BITEMBED further trains output embeddings to support multiple storage precisions meeting different storage needs in various scenarios. Experiments on MMTEB (eng, v2) with Qwen3-0.6B and Gemma3-270M show that BITEMBED is largely comparable to full precision teacher embedders. Moreover, BITEMBED flexibly obtains text embeddings of various precisions, achieving a trade-off between performance and storage cost.