AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Entropy-Based Block Pruning for Efficient Large Language Models

Liangwei Yang, Yuhui Xu, Juntao Tan, Doyen Sahoo, silvio savarese, Caiming Xiong, Huan Wang, Shelby Heinecke

ICLR 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Layer-wise pruning of LLMs · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
prune attention with entropy criterion instead of LLMDrop (16 blocks)Llama3.1-8B · Avg 11 benchmarks, 16 blocks prunedaverage accuracy: 0.4354 -> 0.4781Improved
prune attention with entropy criterion instead of LLMDrop (12 blocks)Mistral-7B-v0.3 · Avg 11 benchmarks, 12 blocks prunedaverage accuracy: 0.5476 -> 0.5757Improved
prune attention with entropy criterion instead of LLMDrop (4 blocks)Llama3.1-8B · Avg 11 benchmarks, 4 blocks prunedaverage accuracy: 0.6283 -> 0.6271No clear effect
entropy layer pruning instead of ShortGPT (8 blocks)Llama3.1-8B · Avg 11 benchmarks, 8 blocks prunedaverage accuracy: 0.3824 -> 0.5133Improved
entropy layer pruning instead of ShortGPT (16 blocks)Llama3.1-8B · Avg 11 benchmarks, 16 blocks prunedaverage accuracy: 0.3251 -> 0.3199No clear effect
entropy layer pruning instead of ShortGPT (12 blocks)Mistral-7B-v0.3 · Avg 11 benchmarks, 12 blocks prunedaverage accuracy: 0.3397 -> 0.3777Improved
prune attention blocks instead of whole layers with entropy criterion (8 blocks)EntroDrop on Llama3.1-8B · Avg 11 benchmarks, 8 blocks prunedaverage accuracy: 0.5133 -> 0.6265Improved
change calibration dataset (C4, Wikitext, Medicine, Law) (ablation)EntroDrop · pruning 12 attention layersaverage accuracyNo clear effect
use Bucket or KNN entropy estimation instead of Renyi (ablation)EntroDrop · deleting 12 attention layersaverage accuracyImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy