Challenge: Existing quantization techniques have been categorized as 'simple' and 'highly efficient' however, their configurations vary from each other and cannot be fairly compared .
Approach: They propose a plug-and-play compression toolkit to explore the impact of quantization.
Outcome: The proposed toolkit explores the impact of quantization on large language models.

Similar Papers

A Comprehensive Evaluation of Quantization Strategies for Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Quantization studies have focused on instruction-tuned LLMs, leaving their performance on other benchmarks unclear.
Approach: They propose a framework to evaluate quantized large language models using four dimensions . they propose to reduce the bits needed for model weights or activations with minimal performance loss .
Outcome: The proposed framework can retain comparable performance to non-quantized LLMs on most benchmarks.
When Compression Meets Model Compression: Memory-Efficient Double Compression for Large Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) exhibit excellent performance in various tasks, but memory requirements present a challenge when deploying on memory-limited devices.
Approach: They propose a framework to compress LLM after quantization further, achieving about 2.2x compression ratio.
Outcome: The proposed model can achieve 40% reduction in memory size with negligible loss in accuracy and inference speed.
The Cost of Compression: Investigating the Impact of Compression on Parametric Knowledge in Language Models (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing research on LLM compression focuses on general metrics like perplexity or downstream task accuracy.
Approach: They propose to quantify the effect of pruning and quantization on model quality . they use the LAMA and LM-Harness benchmarks to quantify compression techniques .
Outcome: The proposed compression techniques provide faster inference, smaller memory footprints, and enables local deployment.
Comparing Text Compression Capabilities of Large Language Models with Traditional Compression Algorithms (2026.eacl-srw)

Copied to clipboard

Challenge: Experimental results show that large language models outperform baselines on non-English datasets . traditional methods remained dataset-agnostic, and the results suggest that current methods are impractical for the compression task.
Approach: They evaluate the non-English and unstructured text compression performance of Large Language Models . they compare them with traditional baselines on datasets from eight most widely spoken languages .
Outcome: The evaluated LLM outperformed baselines on non-English datasets . the results show that the current methods are highly impractical for the compression task .
LVLM-Compress-Bench: Benchmarking the Broader Impact of Large Vision-Language Model Compression (2025.findings-naacl)

Copied to clipboard

Challenge: LVLMs have been shown to perform well on simple uni-modal benchmarks, but their detailed study on multi-modal models is still lacking.
Approach: They propose a framework to analyze the impact of compression on LVLMs on multi-modal input driven tasks.
Outcome: The proposed framework analyzes the impact of compression on generative performance of large vision language models on multi-modal input driven tasks.
Revisiting Block-based Quantisation: What is Important for Sub-8-bit LLM Inference? (2023.emnlp-main)

Copied to clipboard

Challenge: Existing quantisation methods mainly focus on 8-bit LLMs . a lack of scaling offsets in the quantisation process limits the use of LLM inference.
Approach: They propose to use block quantisations to reduce scaling offsets in Large language models . they find that the block quantizations reduce scaling only from an arithmetic perspective .
Outcome: The proposed methods reduce scaling offsets solely from an arithmetic perspective without additional treatments in the computational path.
LSDC: An Efficient and Effective Large-Scale Data Compression Method for Supervised Fine-tuning of Large Language Models (2025.findings-naacl)

Copied to clipboard

Challenge: Large Language Models (LLMs) are expanding in scale and size, increasing computational costs . large-scale data compression techniques can reduce the size of training datasets while maintaining data integrity.
Approach: They propose a large-scale data compression method to reduce the size of training data . they use a bifurcated quantization strategy to maximize the diversity of samples .
Outcome: The proposed method significantly reduces the size of training data while maximizing the submodular gain.
When Quantization Affects Confidence of Large Language Models? (2024.findings-naacl)

Copied to clipboard

Challenge: Existing studies have shown that quantization compromises performance and exacerbates biases in Large Language Models.
Approach: They propose an explanation for quantization loss based on confidence levels . they propose a range of efficient compression and acceleration methods including quan-tization .
Outcome: The proposed methods show that quantization decreases confidence regarding true labels and that it exacerbates biases across different scales.
LLM-QAT: Data-Free Quantization Aware Training for Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Several post-training quantization methods have been shown to perform well down to 8-bits.
Approach: They propose a data-free distillation method that leverages generations produced by the pre-trained model to quantize any generative model independent of its training data.
Outcome: The proposed method outperforms SoTA PTQ and LLaMA models at low bit precision.
LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models (2023.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) are increasingly lengthy and require longer prompts . this paper presents a coarse-to-fine prompt compression method to reduce cost and increase performance.
Approach: They propose a coarse-to-fine prompt compression method that maintains semantic integrity under high compression ratios and a token-level iterative compression algorithm to better model the interdependence between compressed contents.
Outcome: The proposed method yields state-of-the-art performance and allows for up to 20x compression with little performance loss over four datasets from different scenarios.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations