Data-Free Pruning of Self-Attention Layers in LLMs

arXiv:2512.20636 · cs.LG, cs.AI · Submitted 2025-12-03 · Read on arXiv

cs.LG, cs.AI

Submitted: 2025-12-03

Updated: 2026-09-29

Terminology

• Pruning — 3× in this paper · explained in 4 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 7 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes

Sources

• Mosaic: Composite Projection Pruning for Resource-efficient LLMs
• Not All Layers of LLMs Are Necessary During Inference
• GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
• The Unreasonable Ineffectiveness of the Deeper Layers
• What Matters in Transformers? Not All Attention is Needed
• ShortGPT: Layers in Large Language Models are More Redundant Than You Expect
• Pointer Sentinel Mixture Models
• LLaMA: Open and Efficient Foundation Language Models
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• The Llama 3 Herd of Models
• GPT-4 Technical Report
• Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity
• MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks