arXiv cs.LG
· Papers
On the Limits of Layer Pruning for Generative Reasoning in Large Language Models
arXiv:2602.01997v3 Announce Type: replace Abstract: Recent work has shown that layer pruning can effectively compress large language models (LLMs) while retaining strong performance on classification benchmarks, often with little or no finetuning. In contrast, generative reasoning tasks, such as GSM8K and HumanEvaltex