Emergent Abilities in Large Language Models: A Survey

• URL: http://arxiv.org/abs/2503.05788v2
• Date: Fri, 14 Mar 2025 13:28:04 GMT
• Title: Emergent Abilities in Large Language Models: A Survey
• Authors: Leonardo Berti, Flavio Giorgi, Gjergji Kasneci,
• Abstract summary: Large Language Models (LLMs) are leading a new technological revolution as one of the most promising research streams toward artificial general intelligence.<n>The scaling of these models has been linked to various so-called emergent abilities that were previously unobserved.<n>These abilities range from advanced reasoning and in-context learning to coding and problem-solving.<n>Despite their transformative potential, emergent abilities remain poorly understood, leading to misconceptions about their definition, nature, predictability, and implications.
• Score: 9.50669909278749
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Large Language Models (LLMs) are leading a new technological revolution as one of the most promising research streams toward artificial general intelligence. The scaling of these models, accomplished by increasing the number of parameters and the magnitude of the training datasets, has been linked to various so-called emergent abilities that were previously unobserved. These emergent abilities, ranging from advanced reasoning and in-context learning to coding and problem-solving, have sparked an intense scientific debate: Are they truly emergent, or do they simply depend on external factors, such as training dynamics, the type of problems, or the chosen metric? What underlying mechanism causes them? Despite their transformative potential, emergent abilities remain poorly understood, leading to misconceptions about their definition, nature, predictability, and implications. In this work, we shed light on emergent abilities by conducting a comprehensive review of the phenomenon, addressing both its scientific underpinnings and real-world consequences. We first critically analyze existing definitions, exposing inconsistencies in conceptualizing emergent abilities. We then explore the conditions under which these abilities appear, evaluating the role of scaling laws, task complexity, pre-training loss, quantization, and prompting strategies. Our review extends beyond traditional LLMs and includes Large Reasoning Models (LRMs), which leverage reinforcement learning and inference-time search to amplify reasoning and self-reflection. However, emergence is not inherently positive. As AI systems gain autonomous reasoning capabilities, they also develop harmful behaviors, including deception, manipulation, and reward hacking. We highlight growing concerns about safety and governance, emphasizing the need for better evaluation frameworks and regulatory oversight.

Related papers

• The Superalignment of Superhuman Intelligence with Large Language Models [63.96120398355404]
  We discuss the concept of superalignment from the learning perspective to answer this question. We highlight some key research problems in superalignment, namely, weak-to-strong generalization, scalable oversight, and evaluation. We present a conceptual framework for superalignment, which consists of three modules: an attacker which generates adversary queries trying to expose the weaknesses of a learner model; a learner which will refine itself by learning from scalable feedbacks generated by a critic model along with minimal human experts; and a critic which generates critics or explanations for a given query-response pair, with a target of improving the learner by criticizing.
  arXiv  Detail & Related papers  (2024-12-15T10:34:06Z)
• Weak-to-Strong Generalization beyond Accuracy: a Pilot Study in Safety, Toxicity, and Legal Reasoning [10.752609242505953]
  Traditional alignment methods rely on human feedback to fine-tune models. Superhuman models whose outputs may surpass human understanding poses significant challenges. Recent works use weak supervisors to elicit knowledge from much stronger models.
  arXiv  Detail & Related papers  (2024-10-16T14:40:32Z)
• Mechanistic Interpretability for AI Safety -- A Review [28.427951836334188]
  This review explores mechanistic interpretability. Mechanistic interpretability could help prevent catastrophic outcomes as AI systems become more powerful and inscrutable.
  arXiv  Detail & Related papers  (2024-04-22T11:01:51Z)
• Enabling High-Level Machine Reasoning with Cognitive Neuro-Symbolic Systems [67.01132165581667]
  We propose to enable high-level reasoning in AI systems by integrating cognitive architectures with external neuro-symbolic components. We illustrate a hybrid framework centered on ACT-R and we discuss the role of generative models in recent and future applications.
  arXiv  Detail & Related papers  (2023-11-13T21:20:17Z)
• A Survey on Transferability of Adversarial Examples across Deep Neural Networks [53.04734042366312]
  adversarial examples can manipulate machine learning models into making erroneous predictions. The transferability of adversarial examples enables black-box attacks which circumvent the need for detailed knowledge of the target model. This survey explores the landscape of the adversarial transferability of adversarial examples.
  arXiv  Detail & Related papers  (2023-10-26T17:45:26Z)
• Interpretable Imitation Learning with Dynamic Causal Relations [65.18456572421702]
  We propose to expose captured knowledge in the form of a directed acyclic causal graph. We also design this causal discovery process to be state-dependent, enabling it to model the dynamics in latent causal graphs. The proposed framework is composed of three parts: a dynamic causal discovery module, a causality encoding module, and a prediction module, and is trained in an end-to-end manner.
  arXiv  Detail & Related papers  (2023-09-30T20:59:42Z)
• Are Emergent Abilities in Large Language Models just In-Context Learning? [46.561464069450444]
  We present a novel theory that explains emergent abilities, taking into account their potential confounding factors. Our findings suggest that purported emergent abilities are not truly emergent, but result from a combination of in-context learning, model memory, and linguistic knowledge.
  arXiv  Detail & Related papers  (2023-09-04T20:54:11Z)
• Beyond Interpretable Benchmarks: Contextual Learning through Cognitive and Multimodal Perception [0.0]
  This study contends that the Turing Test is misinterpreted as an attempt to anthropomorphize computer systems. It emphasizes tacit learning as a cornerstone of general-purpose intelligence, despite its lack of overt interpretability.
  arXiv  Detail & Related papers  (2022-12-04T08:30:04Z)
• On the Opportunities and Risks of Foundation Models [256.61956234436553]
  We call these models foundation models to underscore their critically central yet incomplete character. This report provides a thorough account of the opportunities and risks of foundation models. To tackle these questions, we believe much of the critical research on foundation models will require deep interdisciplinary collaboration.
  arXiv  Detail & Related papers  (2021-08-16T17:50:08Z)
• Causal World Models by Unsupervised Deconfounding of Physical Dynamics [20.447000858907646]
  The capability of imagining internally with a mental model of the world is vitally important for human cognition. We propose Causal World Models (CWMs) that allow unsupervised modeling of relationships between the intervened and alternative futures. We show reductions in complexity sample for reinforcement learning tasks and improvements in counterfactual physical reasoning.
  arXiv  Detail & Related papers  (2020-12-28T13:44:36Z)
• Explainability in Deep Reinforcement Learning [68.8204255655161]
  We review recent works in the direction to attain Explainable Reinforcement Learning (XRL) In critical situations where it is essential to justify and explain the agent's behaviour, better explainability and interpretability of RL models could help gain scientific insight on the inner workings of what is still considered a black box.
  arXiv  Detail & Related papers  (2020-08-15T10:11:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.