提出量化大模型计算密度的新方法，发现其处理过程实际很密集。
Sparse or Dense? A Mechanistic Estimation of Computation Density in Transformer-based LLMs
- 基于机制可解释性设计计算密度估计器
- 发现模型处理普遍为密集计算，且随输入动态变化
- 适合关注模型内部机理与效率优化的研究者
基于Transformer的大语言模型（LLM）包含数十亿参数，构成深层宽广的计算图。现有研究认为可大幅剪枝参数而影响甚微，暗示计算分布不均。本文提出一种系统量化计算密度的方法，基于机制可解释性设计密度估计器。实验表明：（1）与普遍假设相反，LLM处理通常涉及密集计算；（2）计算密度具有动态性，模型会根据输入在稀疏与密集模式间切换；（3）不同模型对同一输入的密度呈现显著相关性，说明输入类型决定密度高低。进一步分析发现，预测罕见词需要更高密度，增加上下文长度常导致密度下降。该密度估计器有助于深入理解LLM内部运作机制，挑战其符号化解读。
原文摘要 · Abstract (English)
Transformer-based large language models (LLMs) are comprised of billions of parameters arranged in deep and wide computational graphs. Several studies on LLM efficiency optimization argue that it is possible to prune a significant portion of the parameters, while only marginally impacting performance. This suggests that the computation is not uniformly distributed across the parameters. We introduce here a technique to systematically quantify computation density in LLMs. In particular, we design a density estimator drawing on mechanistic interpretability. We experimentally test our estimator and find that: (1) contrary to what has been often assumed, LLM processing generally involves dense computation; (2) computation density is dynamic, in the sense that models shift between sparse and dense processing regimes depending on the input; (3) per-input density is significantly correlated across LLMs, suggesting that the same inputs trigger either low or high density. Investigating the factors influencing density, we observe that predicting rarer tokens requires higher density, and increasing context length often decreases the density. We believe that our computation density estimator will contribute to a better understanding of the processing at work in LLMs, challenging their symbolic interpretation.
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。