大模型部署时性能暴跌，这篇论文揭示了原因并给出解决方案。
Model Hemorrhage and the Robustness Limits of Large Language Models
- 发现模型压缩、剪枝等操作会引发性能连锁衰退
- 识别出注意力机制易受层扩展破坏，量化导致信息丢失
- 提出动态量化、梯度剪枝等三策略提升部署鲁棒性
大型语言模型（LLMs）在自然语言处理任务中表现优异，但在通过量化、剪枝或解码策略调整进行部署时会出现显著性能下降。我们定义该现象为模型出血——由参数修改和架构变化引发的性能衰退。通过对多种LLM框架的系统分析，发现关键脆弱模式：层扩展常破坏注意力机制，压缩技术引发信息损失级联，解码调整放大预测偏差。研究揭示变换器架构存在固有的鲁棒性阈值，决定了不同修改方式下的出血严重程度。我们提出三种缓解策略：梯度感知剪枝保留关键权重路径，动态量化缩放维持激活完整性，解码校准使生成轨迹与原始模型分布对齐。本工作建立了评估模型适应过程中稳定性的基础指标，提供了高效部署下保持性能的实用指南。研究深化了对大规模语言模型在架构转换下神经网络韧性的理解。
原文摘要 · Abstract (English)
Large language models (LLMs) demonstrate strong performance across natural language processing tasks, yet undergo significant performance degradation when modified for deployment through quantization, pruning, or decoding strategy adjustments. We define this phenomenon as model hemorrhage - performance decline caused by parameter alterations and architectural changes. Through systematic analysis of various LLM frameworks, we identify key vulnerability patterns: layer expansion frequently disrupts attention mechanisms, compression techniques induce information loss cascades, and decoding adjustments amplify prediction divergences. Our investigation reveals transformer architectures exhibit inherent robustness thresholds that determine hemorrhage severity across modification types. We propose three mitigation strategies: gradient-aware pruning preserves critical weight pathways, dynamic quantization scaling maintains activation integrity, and decoding calibration aligns generation trajectories with original model distributions. This work establishes foundational metrics for evaluating model stability during adaptation, providing practical guidelines for maintaining performance while enabling efficient LLM deployment. Our findings advance understanding of neural network resilience under architectural transformations, particularly for large-scale language models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。