Challenge: Existing methods for model pruning only perform optimally within specific sparsity ranges.
Approach: They propose a pruning method that reduces model size by eliminating redundant parameters . they compare it with OptiPrune, which adapts non-uniform sparsity with adaptive deviation .
Outcome: The proposed method reduces model size and maintains performance despite large size and high computational demands.

Similar Papers

FISTAPruner: Layer-wise Post-training Pruning for Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Existing pruning methods require inefficient retraining for billion-scale LLMs or rely on heuristicically designed metrics to determine pruning masks, leading to performance degradation.
Approach: They propose a convex optimization model that induces sparsity in large language models by leveraging FISTA.
Outcome: The proposed method can remove 50% of model parameters while retaining 98.6% and 95.6% of the zero-shot performance.
Towards Robust Pruning: An Adaptive Knowledge-Retention Pruning Strategy for Language Models (2023.emnlp-main)

Copied to clipboard

Challenge: Existing pruning strategies struggle to enhance robustness against adversarial attacks when continually increasing model sparsity and require a retraining process.
Approach: They propose a pruning strategy that replicates embedding space and feature space of dense language models and aims to conserve more pre-trained knowledge during the pruning process.
Outcome: The proposed pruning strategy replicates embedding space and feature space of dense language models, aiming to conserve more pre-trained knowledge during the pruning process.
Pruning Foundation Models for High Accuracy without Retraining (2024.findings-emnlp)

Copied to clipboard

Challenge: Despite the superior performance of foundation models, it is challenging to deploy large language models in practical applications due to their massive parameters and computations.
Approach: They propose a pruning algorithm to prune LLMs in one-shot without retraining . they propose retrainable pruning algorithms to prune multiple weights in LLM .
Outcome: The proposed pruning methods perform better than baseline pruning methods on sparse and unstructured sparsity models.
WRP: Weight Recover Prune for Structured Sparsity (2024.acl-long)

Copied to clipboard

Challenge: Existing pruning and quantization algorithms could compress LLMs to 4 bits without retraining.
Approach: They propose a method to prune models using a minimal set of critical weights . they compare the method to a 2:4 structured sparsity method .
Outcome: The proposed method outperforms other methods on LLAMA2 and OPT models while maintaining the efficiency of the compression.
DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization (2025.acl-long)

Copied to clipboard

Challenge: Structured pruning reduces model size but often causes uneven degradation across domains, leading to biased performance.
Approach: They propose a method that dynamically adjusts the data distribution during training to restore balanced performance across heterogeneous and multi-tasking data.
Outcome: Experiments in monolingual and multilingual settings show that the proposed method surpasses similarly sized models in pruning and continued pretraining over perplexity, downstream tasks, and instruction tuning.
Pruning Pre-trained Language Models with Principled Importance and Self-regularization (2023.findings-acl)

Copied to clipboard

Challenge: Pre-trained language models often contain a vast amount of parameters, posing nontrivial requirements for storage and computation.
Approach: They propose a pruning method where model prediction is regularized by the latest checkpoint with increasing sparsity throughout pruning.
Outcome: The proposed approach is effective at sparsity levels, and can be applied to natural language understanding, question answering, and data-to-text generation tasks.
Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient (2025.acl-long)

Copied to clipboard

Challenge: Recent pruning methods rely on heuristically hand-crafted metrics, leading to suboptimal performance.
Approach: They propose a method that optimizes pruning masks by minimizing back-propagation . they learn an underlying Bernoulli distribution to sample binary pruning mask samples .
Outcome: The proposed method is able to support global and heterogeneous pruning without back-propagation.
Pruning Pre-trained Language Models Without Fine-Tuning (2023.acl-long)

Copied to clipboard

Challenge: Existing methods to prune Pre-trained Language Models (PLMs) are overparameterized and require fine-tuning.
Approach: They propose a pruning method that uses first-order pruning to prune PLMs while fine-tuning the remaining weights.
Outcome: The proposed method outperforms first-order pruning and zero-order methods at sparsity levels.
GAP: a Global Adaptive Pruning Method for Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Existing structured pruning methods employ uniform compression rates across network layers, neglecting the varying importance of different network depths.
Approach: They propose a pruning framework that minimizes global capability loss by layer-adaptive pruning rates.
Outcome: The proposed approach achieves comparable performance with state-of-the-art methods at high pruning rates and shows significant advantages at low pruning rates.
Probing Structured Pruning on Multilingual Pre-trained Models: Settings, Algorithms, and Efficiency (2022.acl-long)

Copied to clipboard

Challenge: Structured pruning has been extensively studied on monolingual pre-trained models . but little attention has been paid to evaluating the effectiveness of structured pruning on multilingual models.
Approach: They investigate settings, algorithms, and efficiency of structured pruning on multilingual models . authors propose a simple approach that allows training the model once and adapting to different model sizes at inference .
Outcome: The proposed approach allows training the model once and adapting to different model sizes at inference.

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