Papers with LLM pruning

5 papers
OptiPrune: Effective Pruning Approach for Every Target Sparsity (2025.coling-main)

Copied to clipboard

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.
CFSP: An Efficient Structured Pruning Framework for LLMs with Coarse-to-Fine Activation Information (2025.coling-main)

Copied to clipboard

Challenge: Existing LLM pruning works focus on unstructured pruning, which typically requires special hardware support for a practical speed-up.
Approach: They propose a network pruning framework that leverages both coarse and fine-grained activation information as an importance criterion to guide pruning.
Outcome: The proposed framework outperforms existing pruning methods on diverse models across sparsity budgets.
PPC-GPT: Federated Task-Specific Compression of Large Language Models via Pruning and Chain-of-Thought Distillation (2025.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) are becoming more popular and are gaining widespread use in artificial intelligence.
Approach: They propose a unified framework that addresses both privacy preservation and model compression in federated settings.
Outcome: The proposed framework maintains competitive performance comparable to full-sized LLMs while ensuring robust privacy protection through its federated architecture.
Is C4 Dataset Optimal for Pruning? An Investigation of Calibration Data for LLM Pruning (2024.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to prune LLMs rely on the C4 dataset as calibration data . arithmetic datasets perform better than pre-training datasets for pruning, whereas chain-of-thought is only useful on certain tasks.
Approach: They evaluate the selection of calibration data for LLM pruning across a wide range of datasets . they find that C4 is not the optimal calibration data, and that CoT is only useful on certain tasks.
Outcome: The chosen calibration data significantly impacts the performance of pruned LLMs, the authors found . their results shed light on the importance of carefully selecting calibration data for LLM pruning .
Pruning Weights but Not Truth: Safeguarding Truthfulness While Pruning LLMs (2025.findings-emnlp)

Copied to clipboard

Challenge: Neural network pruning disrupts LLMs’ internal activation features crucial for lie detection . layer-wise pruning sparsity inadvertently removes crucial weights, failing to improve lie detection performance despite its reliance on the most crucial LLM layer.
Approach: They propose a pruning approach that places greater emphasis on layers with more activation outliers and stronger discriminative features simultaneously.
Outcome: The proposed approach improves the hallucination detection for pruned LLMs (achieving 88% accuracy at 50% sparsity) and enhances their performance on TruthfulQA.

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