mlsanityData to 14 Oct 2026

Large Language Models and Emergence: A Complex Systems Perspective

arXiv 2506.11135 ↗First posted 10 Jun 2025cs.CL cs.AI cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 22 of its 73 references that are in the map. First posted on arXiv 10 Jun 2025.

Builds on

22 of 73 references.

References · 22

  1. 2020Scaling Laws for Neural Language Modelscited by 6,586
  2. 2022Emergent Abilities of Large Language Modelscited by 2,512
  3. 2019Deep Double Descent: Where Bigger Models and More Data Hurtcited by 672
  4. 2024GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Modelscited by 550
  5. 2023Are Emergent Abilities of Large Language Models a Mirage?cited by 523
  6. 2022Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Taskcited by 431
  7. 2023Emergent Linear Representations in World Models of Self-Supervised Sequence Modelscited by 319
  8. 2022Emergent Analogical Reasoning in Large Language Modelscited by 240
  9. 2023Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMscited by 124
  10. 2024Evaluating the World Model Implicit in a Generative Modelcited by 113
  11. 2023Are Emergent Abilities in Large Language Models just In-Context Learning?cited by 109
  12. 2023Large Language Models as Tax Attorneys: A Case Study in Legal Capabilities Emergencecited by 42
10 more
  1. 2023Double Descent Demystified: Identifying, Interpreting & Ablating the Sources of a Deep Learning Puzzlecited by 37
  2. 2025Emergent Abilities in Large Language Models: A Surveycited by 37
  3. 2023A U-turn on Double Descent: Rethinking Parameter Counting in Statistical Learningcited by 33
  4. 2024LLMs learn governing principles of dynamical systems, revealing an in-context neural scaling lawcited by 32
  5. 2023Position: Key Claims in LLM Research Have a Long Tail of Footnotescited by 20
  6. 2023A Rainbow in Deep Network Black Boxescited by 18
  7. 2024Phase transition in large language models and the criticality of natural languagescited by 13
  8. 2023Numeracy from Literacy: Data Science as an Emergent Skill from Large Language Modelscited by 8
  9. 2023On Principles of Emergent Organizationcited by 4
  10. 2023Emergence and Function of Abstract Representations in Self-Supervised Transformerscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 5.

7 papers.

  1. 2026If LLMs Have Human-Like Attributes, Then So Does Age of Empires IIcited by 2
  2. 2025Relative-Based Scaling Law for Neural Language Modelscited by 1
  3. 2025Implicature in Interaction: Understanding Implicature Improves Alignment in Human-LLM Interactioncited by 0
  4. 2026Emergence is Overrated: AGI as an Archipelago of Expertscited by 0
  5. 2026Arithmetic Pedagogy for Language Modelscited by 0
  6. 2026The Role of Rigor in Artificial Intelligencecited by 0
  7. 2026Population Physics, Population Problems: Safety and Emergence in LLM Societiescited by 0