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

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.

FastE: Readout-Triggered Token Compression for LLM Embedding Inference

FastE is a training‑free, plug‑and‑play method that compresses token prefixes in large language model (LLM) embedding inference. It uses a shared fixed threshold on batch‑mean readout‑prefix alignment to decide when to compress and ranks prefix states by readout attention scores to keep the most important ones. Experiments on Qwen3‑Embedding models show that FastE can cut decoder‑backbone FLOPs by over 40% while preserving more than 99% of the original ranking quality across multiple benchmarks and tasks.

Lossy Compressive Text Autoencoders

The paper introduces a lossy compressive text autoencoder that learns a compressed latent representation of text by applying residual downscaling and upscaling along the time axis, culminating in a low‑dimensional discrete bottleneck. The authors evaluate various quantization methods, training objectives, and datasets, measuring reconstruction quality with BLEU and LLM‑based semantic judgments, and also test downstream performance on question‑answering and semantic similarity tasks. Their results show that the compressed representations achieve compression rates comparable to lossless algorithms (2.24 bits per byte on web text) while maintaining strong reconstruction and downstream task performance.

A KAN-based Non-linear Factorization for Embedding Layer Compression

arXiv:2610.29424v1 Announce Type: new Abstract: Among existing embedding compression approaches, low-rank factorization provides a simple and mathematically principled solution by approximating the e...

Compressing Sequences in the Latent Embedding Space: $K$-Token Merging for Large Language Models

The paper introduces K-Token Merging, a latent-space compression method that merges each contiguous block of K token embeddings into a single embedding using a lightweight encoder. The compressed sequence is then processed by a LoRA-adapted large language model, while generation continues in the original vocabulary. Experiments on tasks such as structural reasoning, sentiment classification, and code editing demonstrate that K-Token Merging achieves up to 75% input length reduction with minimal performance loss, placing it on the Pareto frontier of performance versus compression.

Choosing a Text Embedding Model: A Practical Benchmarking and Decision Framework

arXiv:2607. 23507v1 Announce Type: cross Abstract: Choosing the right text embedding model is one of the most consequential -- and most frequently under-examined -- decisions in building a retrieval or search system, yet the model that tops a leaderboard is rarely the best choice for a given deployment.

VQ-Logits: Compressing the Output Bottleneck of Large Language Models via Vector Quantized Logits

arXiv:2505.10202v2 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved remarkable success but face significant computational and memory challenges, particularly due to their e...

CausalEmbed: Auto-Regressive Multi-Vector Generation in Latent Space for Visual Document Embedding

CausalEmbed is an auto‑regressive method for generating compact multi‑vector embeddings in visual document retrieval. By using iterative margin loss during contrastive training, it reduces the number of visual tokens needed by 30‑155× while keeping performance competitive across different backbones and benchmarks. The approach offers efficient training, scalable test‑time performance, and a flexible scaling strategy for multi‑vector representations.

Squeezing More from Limited Data with Recursive Transformers

The paper investigates how to effectively pre‑train language models when the data budget is limited but compute is plentiful. It shows that increasing model size only improves performance up to an optimal point, after which overfitting degrades generalization, and that this optimal size varies with both the data budget and downstream tasks. To overcome the inefficiencies of standard Transformers in this regime, the authors propose recursive Transformers that reuse a shared block across depth and employ factorized embeddings, achieving better results than standard models on 10M–100M word pre‑training budgets and competitive performance with BabyLM Challenge 2025 winners.

Generative Embedding Benchmark: How Much Information Survives in a Dense Embedding?

The paper introduces the Generative Embedding Benchmark (GEB), which evaluates how much content from an embedding can be recovered by a decoder that only has access to the frozen embedding and a question, without the original image or intermediate features. GEB uses a curated visual‑question‑answering dataset with 1,800 development and 900 test items covering natural images, scene text, and visual documents. Experiments on seven public embedding models show that visual‑only scores range from 28.25 to 33.21, while joint image‑question encoding boosts scores up to 65.56, revealing that generative readout uncovers information bottlenecks not captured by traditional separability‑based benchmarks.

MTEB: Massive Text Embedding Benchmark

Interpretable Embeddings with Sparse Autoencoders: A Data Analysis Toolkit

arXiv:2512. 10092v2 Announce Type: replace Abstract: Analyzing large-scale text corpora is a core challenge in machine learning, crucial for tasks like identifying undesirable model behaviors or biases in training data.