MMODELYST
Papers/Locality-Aware Redundancy Pruning for LLM Depth Compression
PAP

Locality-Aware Redundancy Pruning for LLM Depth Compression

May 27, 2026

arXiv
Abstract

Large language models are known to contain representational redundancy across network depth, making depth pruning an effective approach for improving inference efficiency. Existing one-shot pruning methods rely on local layer importance or fixed redundancy assumptions across architectures. We propose Locality-Aware Redundancy Pruning (LoRP), a training-free one-shot depth pruning framework guided by representation locality. We show that inter-layer redundancy can be either localized or globally distributed depending on the LLM architecture. To characterize this phenomenon, we introduce Representation Locality Score (RLS), derived from global inter-layer hidden-state similarity. Using a small calibration set, LoRP computes pairwise layer similarity, clusters layers by representational similarity, and allocates pruning according to residual intra-cluster redundancy. Experiments across diverse LLM families show improvements in both perplexity and downstream task accuracy.

Select text to highlight · click a highlight to remove · saved in this browser only
Authors
Vincent-Daniel Yun, Youngrae Kim, Woosang Lim, YoungJin Heo, Minkyu Kim, Sunwoo Lee
Your notes (browser-local)
saved
arXiv:2605.27786