Understanding Performance Collapse in Layer-Pruned Large Language Models via Decision Representation Transitions

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shi, Boyu, Liu, Chang, Gao, ChuanBao, Yang, Xu, Geng, Xin
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

XPERT: Expert Knowledge Transfer for Effective Training of Language Models
by: Liu, Chang, et al.
Published: (2026)

LaCo: Large Language Model Pruning via Layer Collapse
by: Yang, Yifei, et al.
Published: (2024)

Chain-based Distillation for Effective Initialization of Variable-Sized Small Language Models
by: Shi, Boyu, et al.
Published: (2026)

GPTailor: Large Language Model Pruning Through Layer Cutting and Stitching
by: Su, Guinan, et al.
Published: (2025)

Progressively Label Enhancement for Large Language Model Alignment
by: Liu, Biao, et al.
Published: (2024)

A Simple Linear Patch Revives Layer-Pruned Large Language Models
by: Chen, Xinrui, et al.
Published: (2025)

Pruning Large Language Models by Identifying and Preserving Functional Networks
by: Liu, Yiheng, et al.
Published: (2025)

Preference Orchestrator: Prompt-Aware Multi-Objective Alignment for Large Language Models
by: Liu, Biao, et al.
Published: (2025)

PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Paths
by: Chen, Boyu, et al.
Published: (2025)

Exploring the Limits of Pruning: Task-Specific Neurons, Model Collapse, and Recovery in Task-Specific Large Language Models
by: Siam, M. K. Khalidi, et al.
Published: (2026)

A Single Layer to Explain Them All:Understanding Massive Activations in Large Language Models
by: Shi, Zeru, et al.
Published: (2026)

IG-Pruning: Input-Guided Block Pruning for Large Language Models
by: Qiao, Kangyu, et al.
Published: (2025)

VRM: Teaching Reward Models to Understand Authentic Human Preferences
by: Liu, Biao, et al.
Published: (2026)

Instruction-Following Pruning for Large Language Models
by: Hou, Bairu, et al.
Published: (2025)

Efficient Shapley Value-based Non-Uniform Pruning of Large Language Models
by: Sun, Chuan, et al.
Published: (2025)

PIP: Perturbation-based Iterative Pruning for Large Language Models
by: Cao, Yi, et al.
Published: (2025)

Pruning Large Language Models to Intra-module Low-rank Architecture with Transitional Activations
by: Shen, Bowen, et al.
Published: (2024)

Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models
by: Gao, Lang, et al.
Published: (2024)

Fast Large Language Model Collaborative Decoding via Speculation
by: Fu, Jiale, et al.
Published: (2025)

DISP-LLM: Dimension-Independent Structural Pruning for Large Language Models
by: Gao, Shangqian, et al.
Published: (2024)

Bridging Code Graphs and Large Language Models for Better Code Understanding
by: Chen, Zeqi, et al.
Published: (2025)

MINI-LLM: Memory-Efficient Structured Pruning for Large Language Models
by: Cheng, Hongrong, et al.
Published: (2024)

KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse
by: Yang, Jingbo, et al.
Published: (2025)

Adaptive Layer Selection for Layer-Wise Token Pruning in LLM Inference
by: Taniguchi, Rei, et al.
Published: (2026)

Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models
by: Das, Rocktim Jyoti, et al.
Published: (2023)

Toward Adaptive Large Language Models Structured Pruning via Hybrid-grained Weight Importance Assessment
by: Liu, Jun, et al.
Published: (2024)

E$^3$-Pruner: Towards Efficient, Economical, and Effective Layer Pruning for Large Language Models
by: Yuan, Tao, et al.
Published: (2025)

Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient
by: Gao, Yuan, et al.
Published: (2024)

Frustratingly Easy Task-aware Pruning for Large Language Models
by: Tian, Yuanhe, et al.
Published: (2025)

Internal Safety Collapse in Frontier Large Language Models
by: Wu, Yutao, et al.
Published: (2026)

Entropy-Based Block Pruning for Efficient Large Language Models
by: Yang, Liangwei, et al.
Published: (2025)

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning
by: Cao, Mingyu, et al.
Published: (2024)

Understanding and Mitigating Over-refusal for Large Language Models via Safety Representation
by: Zhang, Junbo, et al.
Published: (2025)

Beyond the Leaderboard: Understanding Performance Disparities in Large Language Models via Model Diffing
by: Boughorbel, Sabri, et al.
Published: (2025)

Wanda++: Pruning Large Language Models via Regional Gradients
by: Yang, Yifan, et al.
Published: (2025)

Distilling Fine-grained Sentiment Understanding from Large Language Models
by: Zhang, Yice, et al.
Published: (2024)

Reasoning as State Transition: A Representational Analysis of Reasoning Evolution in Large Language Models
by: Zhang, Siyuan, et al.
Published: (2026)

PAT: Pruning-Aware Tuning for Large Language Models
by: Liu, Yijiang, et al.
Published: (2024)

Logical Phase Transitions: Understanding Collapse in LLM Logical Reasoning
by: Zhang, Xinglang, et al.
Published: (2026)

Large Language Model Pruning
by: Huang, Hanjuan, et al.
Published: (2024)