# Sample-aware Adaptive Structured Pruning for Large Language Models

arXiv: https://arxiv.org/abs/2503.06184 · HTML: https://mlsanity.com/paper/2503.06184/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 34 references that are in the map.
- First posted on arXiv 8 Mar 2025.

## Builds on (most cited first, 25 of 25)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes](https://mlsanity.com/paper/2305.02301/) (2023)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [MetaICL: Learning to Learn In Context](https://mlsanity.com/paper/2110.15943/) (2021)
- [Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning](https://mlsanity.com/paper/2310.06694/) (2023)
- [SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression](https://mlsanity.com/paper/2306.03078/) (2023)
- [Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity](https://mlsanity.com/paper/2310.05175/) (2023)
- [Meta-learning via Language Model In-context Tuning](https://mlsanity.com/paper/2110.07814/) (2021)
- [A Fast Post-Training Pruning Framework for Transformers](https://mlsanity.com/paper/2204.09656/) (2022)
- [Distilling Reasoning Capabilities into Smaller Language Models](https://mlsanity.com/paper/2212.00193/) (2022)
- [Memory-Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer Quantization](https://mlsanity.com/paper/2305.14152/) (2023)
- [Less is More: Task-aware Layer-wise Distillation for Language Model Compression](https://mlsanity.com/paper/2210.01351/) (2022)
- [Distilling Script Knowledge from Large Language Models for Constrained Language Planning](https://mlsanity.com/paper/2305.05252/) (2023)
- [The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights that Matter](https://mlsanity.com/paper/2306.03805/) (2023)
- [MoreauPruner: Robust Pruning of Large Language Models against Weight Perturbations](https://mlsanity.com/paper/2406.07017/) (2024)

## Built on by (most cited first, 1 of 1)

- [Think Before You Prune: Selective Self-Generated Calibration for Pruning Large Reasoning Models](https://mlsanity.com/paper/2511.18864/) (2025)

## Abstract (arXiv)

Large language models (LLMs) have achieved outstanding performance in natural language processing, but enormous model sizes and high computational costs limit their practical deployment. Structured pruning can effectively reduce the resource demands for deployment by removing redundant model parameters. However, the randomly selected calibration data and fixed single importance estimation metrics in existing structured pruning methods lead to degraded performance of pruned models. This study introduces AdaPruner, a sample-aware adaptive structured pruning framework for LLMs, aiming to optimize the calibration data and importance estimation metrics in the structured pruning process. Specifically, AdaPruner effectively removes redundant parameters from LLMs by constructing a structured pruning solution space and then employing Bayesian optimization to adaptively search for the optimal calibration data and importance estimation metrics. Experimental results show that the AdaPruner outperforms existing structured pruning methods on a family of LLMs with varying pruning ratios, demonstrating its applicability and robustness. Remarkably, at a 20% pruning ratio, the model pruned with AdaPruner maintains 97% of the performance of the unpruned model.