从神经科学视角揭示大模型训练中的三阶段突变现象
Triple Phase Transitions: Understanding the Learning Dynamics of Large Language Models from a Neuroscience Perspective
- 通过脑机类比分析模型内部状态与任务表现的动态变化
- 发现训练中出现三次相变：对齐、脱离、再对齐大脑模式
- 为理解大模型能力涌现提供新思路，适合跨领域研究者
大语言模型常表现出突发的能力涌现现象，即在训练过程中某些节点突然获得新能力，这种现象被称为“相变”，但其机制尚不清晰。本文通过整合三个视角——大语言模型与人类大脑的相似性、模型内部状态以及下游任务性能——对这一现象进行综合分析。我们提出一种新的学习动态解释，发现不同训练数据和架构的大模型在训练过程中普遍经历三个相变阶段：(1) 模型开始遵循任务指令时，与整体大脑的对齐度显著上升（脑对齐与指令遵循）；(2) 在下游任务准确率暂时停滞期间，模型与大脑的关联意外下降（脑脱离与停滞）；(3) 当模型具备解决下游任务能力时，与大脑的对齐再次恢复（脑重对齐与巩固）。这些发现揭示了大语言模型相变的潜在机制，为人工智能与神经科学的交叉研究开辟了新路径。
原文摘要 · Abstract (English)
Large language models (LLMs) often exhibit abrupt emergent behavior, whereby new abilities arise at certain points during their training. This phenomenon, commonly referred to as a ''phase transition'', remains poorly understood. In this study, we conduct an integrative analysis of such phase transitions by examining three interconnected perspectives: the similarity between LLMs and the human brain, the internal states of LLMs, and downstream task performance. We propose a novel interpretation for the learning dynamics of LLMs that vary in both training data and architecture, revealing that three phase transitions commonly emerge across these models during training: (1) alignment with the entire brain surges as LLMs begin adhering to task instructions Brain Alignment and Instruction Following, (2) unexpectedly, LLMs diverge from the brain during a period in which downstream task accuracy temporarily stagnates Brain Detachment and Stagnation, and (3) alignment with the brain reoccurs as LLMs become capable of solving the downstream tasks Brain Realignment and Consolidation. These findings illuminate the underlying mechanisms of phase transitions in LLMs, while opening new avenues for interdisciplinary research bridging AI and neuroscience.
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。