Pruning via Causal Attribution Preserves Reasoning Performance in Large Language Models

arXiv:2606.19350 · cs.CL · Submitted 2026-04-27 · Read on arXiv

cs.CL

Submitted: 2026-04-27

Updated: 2026-10-27

Terminology

• Sparsity — 5× in this paper · explained in 5 episodes
• Pruning — 4× in this paper · explained in 4 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 9 episodes
• Causal Attribution Pruning — 1× in this paper
• Language Models (LLMs) — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 9 episodes

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering