mlsanityData to 7 Oct 2026

On the Unexpected Abilities of Large Language Models

arXiv 2308.09720 ↗First posted 9 Aug 2023cs.AI cs.CL cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) are capable of displaying a wide range of abilities that are not directly connected with the task for which they are trained: predicting the next words of human-written texts. In this article, I review recent research investigating the cognitive abilities developed by LLMs and their relation to human cognition. I discuss the nature of the indirect process that leads to the acquisition of these cognitive abilities, their relation to other indirect processes, and the implications for the acquisition of integrated abilities. Moreover, I propose the factors that enable the development of abilities that are related only very indirectly to the proximal objective of the training task. Finally, I discuss whether the full set of capabilities that LLMs could possibly develop is predictable.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 51 of its 77 references that are in the map. First posted on arXiv 9 Aug 2023.

Builds on

51 of 77 references.

References · 51

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  5. 2020Scaling Laws for Neural Language Modelscited by 6,411
  6. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  7. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  8. 2017Deep reinforcement learning from human preferencescited by 3,846
  9. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  10. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  11. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  12. 2022Emergent Abilities of Large Language Modelscited by 2,483
38 more
  1. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
  2. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  3. 2019Language Models as Knowledge Bases?cited by 1,922
  4. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,235
  5. 2022LaMDA: Language Models for Dialog Applicationscited by 1,218
  6. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,199
  7. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
  8. 2021Ethical and social risks of harm from Language Modelscited by 957
  9. 2020How Much Knowledge Can You Pack Into the Parameters of a Language Model?cited by 713
  10. 2022Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learnedcited by 702
  11. 2019Solving Rubik's Cube with a Robot Handcited by 699
  12. 2019BLiMP: The Benchmark of Linguistic Minimal Pairs for Englishcited by 553
  13. 2023Are Emergent Abilities of Large Language Models a Mirage?cited by 515
  14. 2023Faith and Fate: Limits of Transformers on Compositionalitycited by 496
  15. 2022Using cognitive psychology to understand GPT-3cited by 389
  16. 2021Measuring and Improving Consistency in Pretrained Language Modelscited by 361
  17. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 331
  18. 2023Role-Play with Large Language Modelscited by 290
  19. 2023Large Language Models Fail on Trivial Alterations to Theory-of-Mind Taskscited by 288
  20. 2023Pretraining Language Models with Human Preferencescited by 245
  21. 2022Multi-Game Decision Transformerscited by 212
  22. 2021Implicit Representations of Meaning in Neural Language Modelscited by 179
  23. 2019Build it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attackcited by 176
  24. 2023The Capacity for Moral Self-Correction in Large Language Modelscited by 171
  25. 2019oLMpics -- On what Language Model Pre-training Capturescited by 161
  26. 2021Understanding the Capabilities, Limitations, and Societal Impact of Large Language Modelscited by 159
  27. 2023Fundamental Limitations of Alignment in Large Language Modelscited by 152
  28. 2022The Debate Over Understanding in AI's Large Language Modelscited by 142
  29. 2021Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Colorcited by 118
  30. 2022What Artificial Neural Networks Can Tell Us About Human Language Acquisitioncited by 97
  31. 2023Eight Things to Know about Large Language Modelscited by 73
  32. 2023Turning large language models into cognitive modelscited by 66
  33. 2023Call for Papers -- The BabyLM Challenge: Sample-efficient pretraining on a developmentally plausible corpuscited by 62
  34. 2021Shaking the foundations: delusions in sequence models for interaction and controlcited by 61
  35. 2022Do Large Language Models know what humans know?cited by 60
  36. 2023The Vector Grounding Problemcited by 39
  37. 2021Does Vision-and-Language Pretraining Improve Lexical Grounding?cited by 25
  38. 2018Evolutionary Innovations and Where to Find Them: Routes to Open-Ended Evolution in Natural and Artificial Systemscited by 10

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 3; 2025: 2.

5 papers.

  1. 2024Large Language Models and Cognitive Science: A Comprehensive Review of Similarities, Differences, and Challengescited by 48
  2. 2024Large Language Model Benchmarks in Medical Taskscited by 16
  3. 2024Neurosymbolic Graph Enrichment for Grounded World Modelscited by 6
  4. 2025Distinguishing AI-Generated and Human-Written Text Through Psycholinguistic Analysiscited by 3
  5. 2025Fine-Tuning Large Language Models Using EEG Microstate Features for Mental Workload Assessmentcited by 0