arXiv Computation and Language
Debias-SparseGPT: Bias-Aware Pruning for Large Language Models
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv Machine Learning
Aug 27
When Pruning Meets Interpretability: Preserving Sparse Autoencoder Robustness in LLMs
Sparse autoencoders (SAEs) are commonly used to interpret large language models, but their reliability after pruning is unclear. This study shows that pruning’s effect on an SAE is governed by perturbation energy, a covariance-weighted norm, and that magnitude pruning distorts the representation space by ignoring activation geometry. Activation-aware pruning methods such as Wanda and SparseGPT better preserve SAE behavior, and the authors find that middle layers are especially vulnerable, leading them to propose a layer‑wise sparsity allocation that reduces perplexity for a given sparsity level.
arXiv Computation and Language
4d ago
Pruning Laws for Large Language Models
arXiv:2504.04342v2 Announce Type: replace Abstract: Scaling up model parameters and training data consistently improves the performance of large language models (LLMs), but at the cost of rapidly gro...
arXiv Machine Learning
Aug 4
GPrune-LLM: Generalization-Aware Structured Pruning for Large Language Models
arXiv:2603. 13418v2 Announce Type: replace Abstract: Structured pruning is widely applied to compress large language models (LLMs), but its performance depends heavily on how neuron importance is estimated.
arXiv Machine Learning
Jul 30
Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation
arXiv:2510. 00192v3 Announce Type: replace Abstract: Low-rank adaptation (LoRA) has become a widely used paradigm for parameter-efficient fine-tuning of large language models, yet its representational capacity often lags behind full fine-tuning.
arXiv Machine Learning
Aug 10
The Sparsity Whisperer
arXiv:2608. 06630v1 Announce Type: new Abstract: Pruning reduces the inference cost of large language models, but existing criteria primarily preserve large activations or reconstruct layer outputs.
arXiv AI
Aug 28
Frequency Matters: Fast Model-Agnostic Data Curation for Pruning and Quantization
The paper introduces ZipCal, a model‑agnostic data curation method that selects calibration data for post‑training compression of large language models by maximizing lexical diversity using Zipfian power laws. ZipCal outperforms uniform random sampling on pruning benchmarks and matches a state‑of‑the‑art perplexity‑based approach while being roughly 240× faster due to its linear complexity. The authors provide code and experiments at their GitHub repository.