从复杂系统视角分析大模型涌现能力，揭示智能涌现的深层机制。
Large Language Models and Emergence: A Complex Systems Perspective
- 用复杂系统理论解析大模型能力的涌现现象
- 提出量化智能涌现的新方法，发现关键能力在规模增大时突然出现
- 适合对大模型原理和智能本质感兴趣的科研人员
涌现是复杂科学中的核心概念，描述多体系统如何表现出高阶新属性——这些属性可通过低维有效变量和理论来描述，体现了‘更多即不同’的思想。智能正是这种涌现的极致表现，表现为以更低成本、更高效率利用涌现能力解决问题，即‘少即是多’。本文首先审视大语言模型是否展现出涌现能力，回顾多种量化涌现的方法；其次探讨大模型是否具备涌现智能，为理解其内在机制提供新视角。
原文摘要 · Abstract (English)
Emergence is a concept in complexity science that describes how many-body systems manifest novel higher-level properties, properties that can be described by replacing high-dimensional mechanisms with lower-dimensional effective variables and theories. This is captured by the idea "more is different". Intelligence is a consummate emergent property manifesting increasingly efficient -- cheaper and faster -- uses of emergent capabilities to solve problems. This is captured by the idea "less is more". In this paper, we first examine claims that Large Language Models exhibit emergent capabilities, reviewing several approaches to quantifying emergence, and secondly ask whether LLMs possess emergent intelligence.
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。