Distilling Large Embeddings via Hyperspherical Householder Quantization (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for quantizing large embeddings rely on Euclidean quantization, which is poorly aligned with the angular geometry induced by contrastive embeddment training. |
| Approach: | They propose a geometry-aware distillation method that compresses large embeddings into short discrete representations via iterative Householder transformations on the unit hypersphere. |
| Outcome: | The proposed method reduces decoding cost and maintains strong semantic retrieval accuracy. |
Similar Papers
GS-Quant: Granular Semantic and Generative Structural Quantization for Knowledge Graph Completion (2026.acl-long)
Copied to clipboard
| Challenge: | Existing quantization-based approaches to knowledge Graph Completion (KGC) are incomplete. |
| Approach: | They propose a framework that generates semantically coherent discrete codes for KG entities . they introduce a Granular Semantic Enhancement module that injects hierarchical knowledge into the codebook . |
| Outcome: | The proposed framework outperforms existing text-based and embedding-based baselines in the KGC domain. |
M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation (2024.findings-acl)
Copied to clipboard
| Challenge: | In this paper, we introduce a new embedding model for semantic retrieval of more than 100 working languages. |
| Approach: | They propose a new embedding model that supports multi-lingual, cross-lingual and long-document retrieval . they propose integrating relevance scores from different retrieval functionalities into the teacher signal . |
| Outcome: | The proposed model exhibits superior performance on multilingual, cross-lingual, and long-document retrieval benchmarks. |
Compressing Sentence Representation for Semantic Retrieval via Homomorphic Projective Distillation (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing pre-trained language models produce large sentence embeddings, resulting in performance gap between large and small models. |
| Approach: | They propose a method that augments a small Transformer encoder model with learnable projection layers to produce compact sentences while mimicking a large pre-trained language model to retain the sentence representation quality. |
| Outcome: | The proposed method achieves 2.7-4.5 points performance gain on STS and SR tasks while maintaining the quality of the pre-trained language models. |
Exploring Layer-wise Information Effectiveness for Post-Training Quantization in Small Language Models (2026.findings-acl)
Copied to clipboard
He Xiao, Qingyao Yang, Dirui Xie, Wendong XU, Zunhai Su, Runming Yang, Haobo Liu, Wenyong Zhou, Zhengwu Liu, Ngai Wong
| Challenge: | Large language models with billions of parameters are often over-provisioned . smaller models exhibit lower robustness under extreme low-bit quantization . |
| Approach: | They propose a hardware-native, metric-driven post-training quantization framework that keeps uniform bit-width within each layer while mixing precision across layers. |
| Outcome: | LieQ reduces large accuracy gap observed for large language models with billions of parameters while preserving standard multiplication kernels. |
Matching-oriented Embedding Quantization For Ad-hoc Retrieval (2021.emnlp-main)
Copied to clipboard
| Challenge: | Product quantization (PQ) is a widely used technique for ad-hoc retrieval. |
| Approach: | They propose a match-oriented product quantization with a multinoulli contrastive loss objective. |
| Outcome: | The proposed method maximizes matching probability of query and ground-truth key, compared with previous methods on non-supervised datasets. |
xCOMET-lite: Bridging the Gap Between Efficiency and Quality in Learned MT Evaluation Metrics (2024.emnlp-main)
Copied to clipboard
| Challenge: | State-of-the-art trainable machine translation evaluation metrics rely on large encoders . this makes them computationally expensive and inaccessible to researchers with limited resources. |
| Approach: | They propose a method to extract knowledge stored in large encoders and a pipeline for efficient black-box distillation. |
| Outcome: | The proposed model surpasses COMET-22 and BLEURT-20 on the WMT22 dataset by 6.4%. |
CARVQ: Corrective Adaptor with Group Residual Vector Quantization for LLM Embedding Compression (2025.findings-emnlp)
Copied to clipboard
Dayin Gou, Sanghyun Byun, Nilesh Malpeddi, Gabrielle De Micheli, Prathamesh Vaste, Jacob Song, Woo Seong Chung
| Challenge: | Large Language Models typically rely on a large number of parameters for token embedding, leading to substantial storage requirements and memory footprints. |
| Approach: | They propose a corrective Adaptor with group Residual Vector Quantization that can be used to compress the embedding layer without requiring specialized hardware. |
| Outcome: | The proposed corrective adaptor can achieve lower average bitwidth-per-parameter while maintaining reasonable perplexity and accuracy compared to scalar quantization. |
Beyond Dynamic Quantization: An Efficient Static Hierarchical Mix-precision Framework for Near-Lossless LLM Compression (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Existing methods for dynamic quantization are hardware-unfriendly and often lead to large quantization errors in static scenarios. |
| Approach: | They propose a Static Hierarchical Mix-precision Quantization method which quantifies both inter-layer and intra-layer sensitivity through unified derivations involving Hessian. |
| Outcome: | The proposed method achieves 75.58% on zero-shot reasoning tasks while yielding average speedup of 2.86. |
A Frustratingly Easy Post-Training Quantization Scheme for LLMs (2023.emnlp-main)
Copied to clipboard
| Challenge: | Efficient inference is crucial for hyper-scale AI models, including large language models, as their parameter count continues to increase for enhanced performance. |
| Approach: | They propose a quantization scheme that fully utilizes the Transformer structure used in large language models to minimize the frequency of DRAM access while exploiting the parallelism of operations. |
| Outcome: | The proposed method minimizes the frequency of DRAM access while exploiting the parallelism of operations through a dense matrix format. |
Resonating with RoPE: Spectral Quantization for High-Fidelity Key Cache Compression (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to reduce memory footprint of long-context LLMs rely on RoPE-induced oscillations. |
| Approach: | They propose a frequency-domain framework that converts RoPE-induced oscillations into sparse spectral representations. |
| Outcome: | The proposed framework achieves efficient compression with performance comparable to FP16 benchmarks. |