Low-Bit Quantization Favors Undertrained LLMs (2025.acl-long)

Copied to clipboard

Challenge: Larger models or those trained on fewer tokens exhibit less quantization-induced degradation (QiD), while smaller, well-trained models face significant performance losses.
Approach: They propose to use QiD to measure an LLM’s training levels and determine the number of training tokens required for fully training LLMs of various sizes.
Outcome: The proposed scaling laws can predict the quantization performance of different-sized LLMs trained with tokens.

Similar Papers

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.
Why Do Some Inputs Break Low-Bit LLM Quantization? (2025.emnlp-main)

Copied to clipboard

Challenge: Low-bit weight-only quantization reduces memory usage but disproportionately affects certain examples.
Approach: They analyze quantization errors of 50 pairs of methods on large language models and test their hypothesis .
Outcome: The proposed method reduces the memory footprint of large language models while maintaining reasonable performance across benchmarks.
Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical Study (2024.lrec-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) require significant computational resources for deployment and use.
Approach: They propose to use low-bit quantization methods to reduce memory footprint and increase inference rate to improve performance of Large Language Models.
Outcome: The proposed methods can reduce the memory footprint and increase the inference rate of LLMs.
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.
PTQ1.61: Push the Real Limit of Extremely Low-Bit Post-Training Quantization Methods for Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for sub 2-bit quantization introduce an extra 1-bit or more per weight.
Approach: They propose a sub 2-bit post-training quantization method that enables weight quantization to 1.61-bit for the first time.
Outcome: The proposed method reduces the upper bound of quantization error to 1.61-bit for the first time.
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.
Achieving binary weight and activation for LLMs using Post-Training Quantization (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods for quantizing large language models suffer from performance degradation when weights are quantized to 1 bit.
Approach: They propose a post-training quantization framework with W(1+1)A(14) configuration . they propose utilizing Hessian-aware fine-grained grouping along with an EM-based quantization scheme .
Outcome: The proposed method surpasses state-of-the-art (SOTA) LLM quantization baselines on W2A4 across multiple tasks.
Continual Quantization-Aware Pre-Training: When to transition from 16-bit to 1.58-bit pre-training for BitNet language models? (2025.findings-acl)

Copied to clipboard

Challenge: Quantization-aware training of large language models reduces the precision of model parameters and reduces memory usage and energy consumption at inference time.
Approach: They propose a method where models are first trained with 16-bit precision and then transition to 1.58-bit quantization-aware training.
Outcome: The proposed training strategy reduces memory and energy consumption while maintaining model accuracy while reducing memory and inference time.
Does quantization affect models’ performance on long-context tasks? (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models support context windows exceeding 128K tokens, but this comes with significant memory requirements and high inference latency.
Approach: They present the first systematic evaluation of quantized LLMs on tasks with long inputs and long-form outputs.
Outcome: The proposed method preserves accuracy, while 4-bit methods lead to substantial losses . the results highlight the importance of a careful evaluation before deploying quantized LLMs .
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.

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