Papers with post-training quantization
LLM-FP4: 4-Bit Floating-Point Quantized Transformers (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing quantization solutions are integer-based and struggle with bit widths below 8 bits. |
| Approach: | They propose a method for quantizing weights and activations in large language models down to 4-bit floating-point values in a post-training manner. |
| Outcome: | The proposed method outperforms existing methods on common sense zero-shot reasoning tasks by 12.7 points. |
Self-Distilled Quantization: Achieving High Compression Rates in Transformer-Based Language Models (2023.acl-short)
Copied to clipboard
| Challenge: | Existing methods for quantization-aware training and quantization for learning have limitations in dealing with accumulative quantization errors. |
| Approach: | They propose a method that minimizes accumulative quantization errors and outperforms baselines by distilling knowledge from a fine-tuned teacher network. |
| Outcome: | The proposed method minimizes accumulative quantization errors and outperforms baselines on the XGLUE benchmark. |
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. |
AlphaTuning: Quantization-Aware Parameter-Efficient Adaptation of Large-Scale Pre-Trained Language Models (2022.findings-emnlp)
Copied to clipboard
Se Jung Kwon, Jeonghoon Kim, Jeongin Bae, Kang Min Yoo, Jin-Hwa Kim, Baeseong Park, Byeongwook Kim, Jung-Woo Ha, Nako Sung, Dongsoo Lee
| Challenge: | Existing approaches to improve inference efficiency by accelerating model fine-tuning have not been thoroughly explored. |
| Approach: | They propose to combine parameter-efficient adaptation and model compression to accelerate model . they propose to freeze binary parameters and scale scaling factors for target tasks . |
| Outcome: | The proposed algorithm achieves >10x compression ratio under 4-bit quantization and >1,000x reduction in trainable parameters. |
LRQ: Optimizing Post-Training Quantization for Large Language Models by Learning Low-Rank Weight-Scaling Matrices (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for quantizing weights and activations of large language models suffer from non-negligible accuracy drops, especially on massive multitask language understanding. |
| Approach: | They propose a weight-activation quantization method that reconstructs the outputs of an intermediate Transformer block by leveraging low-rank weight-scaling matrices. |
| Outcome: | The proposed method reduces the complexity of the weight-activation quantization techniques while achieving high throughput and reducing inference costs. |
PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models (2023.findings-acl)
Copied to clipboard
Zhuocheng Gong, Jiahao Liu, Qifan Wang, Yang Yang, Jingang Wang, Wei Wu, Yunsen Xian, Dongyan Zhao, Rui Yan
| Challenge: | Quantization is a viable solution for pre-trained language models, but most existing methods are task-specific and require customized training and quantization with a large number of trainable parameters. |
| Approach: | They propose a "quantize before fine-tuning" framework that allows for quantization with a large number of trainable parameters on each individual task. |
| Outcome: | The proposed framework is compatible with quantization-aware training and post-training quantization and corrects quantization errors. |
Improving Conversational Abilities of Quantized Large Language Models via Direct Preference Alignment (2024.acl-long)
Copied to clipboard
| Challenge: | Quantization-aware direct preference optimization (QDPO) improves conversational abilities of quantized LLMs . token-flipping is a critical factor for degraded text generation quality . |
| Approach: | They propose a method that aligns quantized LLMs with their full-precision counterparts, improving conversational abilities. |
| Outcome: | The proposed method outperforms established fine-tuning techniques on two instruction-tuned LLMs in various languages and models, setting a new benchmark for conversational chatbot development. |
Understanding and Overcoming the Challenges of Efficient Transformer Quantization (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in transformer quantization have shown remarkable improvement in many Natural Language Processing tasks and beyond. |
| Approach: | They propose a novel quantization scheme for transformers that can be quantized to ultra-low bit-widths, leading to significant memory savings with a minimum accuracy loss. |
| Outcome: | The proposed methods achieve state-of-the-art results on the GLUE benchmark using BERT, while preserving memory and accuracy. |
Enhancing Computation Efficiency in Large Language Models through Weight and Activation Quantization (2023.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) are proficient in natural language processing tasks, but their deployment is limited by extensive parameter sizes and computational demands. |
| Approach: | They propose a method to enhance computational efficiency in large language models by 4-bit weight and 8-bit activation quantization. |
| Outcome: | The proposed techniques significantly boost task accuracies to levels comparable with full-precision models. |
KurTail : Kurtosis-based LLM Quantization (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Outliers in quantization of large language models make uniform quantization schemes less effective . a new PTQ scheme that leverages Kurtosis-based rotation mitigates outliers . |
| Approach: | They propose a new post-training quantization scheme that leverages Kurtosis-based rotation to mitigate outliers in the activations of large language models. |
| Outcome: | The proposed method outperforms existing quantization methods with 13.3% boost in MMLU accuracy and 15.5% boost in Wiki perplexity. |
FAQ: Mitigating Quantization Error via Regenerating Calibration Data with Family-Aware Quantization (2026.findings-acl)
Copied to clipboard
| Challenge: | representativeness and universality of calibration data remain a bottleneck in quantization accuracy. |
| Approach: | They propose a framework that leverages prior knowledge from LLMs to generate calibration samples . their framework reduces accuracy loss by up to 28.5% compared to baseline . |
| Outcome: | Experiments show that family-aware quantization reduces accuracy loss by up to 28.5% compared to baseline data. |
Benchmarking Post-Training Quantization of Large Language Models under Microscaling Floating Point Formats (2026.acl-long)
Copied to clipboard
| Challenge: | Microscaling Floating-Point (MXFP) is a low-precision format for large language models (LLMs). |
| Approach: | They conduct systematic evaluations of PTQ under Microscaling Floating-Point (MXFP) . they find that MXFP8 consistently achieves near-lossless performance . |
| Outcome: | The proposed method achieves near-lossless performance while MXFP4 introduces substantial accuracy degradation and remains challenging. |