Strategy Coopetition Explains the Emergence and Transience of In-Context Learning

• URL: http://arxiv.org/abs/2503.05631v2
• Date: Mon, 10 Mar 2025 07:13:09 GMT
• Title: Strategy Coopetition Explains the Emergence and Transience of In-Context Learning
• Authors: Aaditya K. Singh, Ted Moskovitz, Sara Dragutinovic, Felix Hill, Stephanie C. Y. Chan, Andrew M. Saxe,
• Abstract summary: In-context learning (ICL) is a powerful ability that emerges in transformer models, enabling them to learn from context without weight updates.<n>Recent work has established emergent ICL as a transient phenomenon that can sometimes disappear after long training times.<n>We propose a minimal mathematical model that reproduces these key dynamics and interactions.
• Score: 24.63934469340368
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In-context learning (ICL) is a powerful ability that emerges in transformer models, enabling them to learn from context without weight updates. Recent work has established emergent ICL as a transient phenomenon that can sometimes disappear after long training times. In this work, we sought a mechanistic understanding of these transient dynamics. Firstly, we find that, after the disappearance of ICL, the asymptotic strategy is a remarkable hybrid between in-weights and in-context learning, which we term "context-constrained in-weights learning" (CIWL). CIWL is in competition with ICL, and eventually replaces it as the dominant strategy of the model (thus leading to ICL transience). However, we also find that the two competing strategies actually share sub-circuits, which gives rise to cooperative dynamics as well. For example, in our setup, ICL is unable to emerge quickly on its own, and can only be enabled through the simultaneous slow development of asymptotic CIWL. CIWL thus both cooperates and competes with ICL, a phenomenon we term "strategy coopetition." We propose a minimal mathematical model that reproduces these key dynamics and interactions. Informed by this model, we were able to identify a setup where ICL is truly emergent and persistent.

Related papers

• ECM: A Unified Electronic Circuit Model for Explaining the Emergence of In-Context Learning and Chain-of-Thought in Large Language Model [64.22300168242221]
  In-Context Learning (ICL) and Chain-of-Thought (CoT) are emerging capabilities in large language models.<n>We propose the Electronic Circuit Model (ECM) to better understand ICL and CoT.<n>We show that ECM effectively predicts and explains LLM performance across a variety of prompting strategies.
  arXiv  Detail & Related papers  (2025-02-05T16:22:33Z)
• Continual Task Learning through Adaptive Policy Self-Composition [54.95680427960524]
  CompoFormer is a structure-based continual transformer model that adaptively composes previous policies via a meta-policy network. Our experiments reveal that CompoFormer outperforms conventional continual learning (CL) methods, particularly in longer task sequences.
  arXiv  Detail & Related papers  (2024-11-18T08:20:21Z)
• Investigating the Pre-Training Dynamics of In-Context Learning: Task Recognition vs. Task Learning [99.05401042153214]
  In-context learning (ICL) is potentially attributed to two major abilities: task recognition (TR) and task learning (TL) We take the first step by examining the pre-training dynamics of the emergence of ICL. We propose a simple yet effective method to better integrate these two abilities for ICL at inference time.
  arXiv  Detail & Related papers  (2024-06-20T06:37:47Z)
• Data Poisoning for In-context Learning [49.77204165250528]
  In-context learning (ICL) has been recognized for its innovative ability to adapt to new tasks. This paper delves into the critical issue of ICL's susceptibility to data poisoning attacks. We introduce ICLPoison, a specialized attacking framework conceived to exploit the learning mechanisms of ICL.
  arXiv  Detail & Related papers  (2024-02-03T14:20:20Z)
• The Transient Nature of Emergent In-Context Learning in Transformers [28.256651019346023]
  Transformer networks can exhibit a surprising capacity for in-context learning (ICL) despite not being explicitly trained for it. We show that the emergence of ICL during transformer training is, in fact, often transient. We find that ICL first emerges, then disappears and gives way to IWL, all while the training loss decreases.
  arXiv  Detail & Related papers  (2023-11-14T18:03:20Z)
• In-Context Exemplars as Clues to Retrieving from Large Associative Memory [1.2952137350423816]
  In-context learning (ICL) enables large language models (LLMs) to learn patterns from in-context exemplars without training. How to choose exemplars remains unclear due to the lack of understanding of how in-context learning works. Our study sheds new light on the mechanism of ICL by connecting it to memory retrieval.
  arXiv  Detail & Related papers  (2023-11-06T20:13:29Z)
• In-Context Learning Learns Label Relationships but Is Not Conventional Learning [60.891931501449726]
  There is currently no consensus about how in-context learning (ICL) ability of Large Language Models works. We provide novel insights into how ICL leverages label information, revealing both capabilities and limitations. Our experiments show that ICL predictions almost always depend on in-context labels and that ICL can learn truly novel tasks in-context.
  arXiv  Detail & Related papers  (2023-07-23T16:54:41Z)
• A Survey on In-context Learning [77.78614055956365]
  In-context learning (ICL) has emerged as a new paradigm for natural language processing (NLP) We first present a formal definition of ICL and clarify its correlation to related studies. We then organize and discuss advanced techniques, including training strategies, prompt designing strategies, and related analysis.
  arXiv  Detail & Related papers  (2022-12-31T15:57:09Z)

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.