Alignment-Constrained Dynamic Pruning for LLMs: Identifying and Preserving Alignment-Critical Circuits

📝 Original Info

• Title: Alignment-Constrained Dynamic Pruning for LLMs: Identifying and Preserving Alignment-Critical Circuits
• ArXiv ID: 2511.07482
• Date: 2025-11-09
• Authors: 정보 없음 (제공된 텍스트에 저자 정보가 포함되어 있지 않음)

📝 Abstract

Large Language Models require substantial computational resources for inference, posing deployment challenges. While dynamic pruning offers superior efficiency over static methods through adaptive circuit selection, it exacerbates alignment degradation by retaining only input-dependent safety-critical circuit preservation across diverse inputs. As a result, addressing these heightened alignment vulnerabilities remains critical. We introduce Alignment-Aware Probe Pruning (AAPP), a dynamic structured pruning method that adaptively preserves alignment-relevant circuits during inference, building upon Probe Pruning. Experiments on LLaMA 2-7B, Qwen2.5-14B-Instruct, and Gemma-3-12B-IT show AAPP improves refusal rates by 50\% at matched compute, enabling efficient yet safety-preserving LLM deployment.

💡 Deep Analysis

📄 Full Content

Reference