中文
相关论文

相关论文: Pretraining task diversity and the emergence of no…

200 篇论文

In-context learning (ICL) is a remarkable capability of pretrained transformers that allows models to generalize to unseen tasks after seeing only a few examples. We investigate empirically the conditions necessary on the pretraining…

机器学习 · 计算机科学 2025-12-11 Chase Goddard , Lindsay M. Smith , Vudtiwat Ngampruetikorn , David J. Schwab

Transformers pretrained on diverse tasks exhibit remarkable in-context learning (ICL) capabilities, enabling them to solve unseen tasks solely based on input contexts without adjusting model parameters. In this paper, we study ICL in one of…

机器学习 · 统计学 2024-03-18 Jingfeng Wu , Difan Zou , Zixiang Chen , Vladimir Braverman , Quanquan Gu , Peter L. Bartlett

In-context learning (ICL) is one of the surprising and useful features of large language models and subject of intense research. Recently, stylized meta-learning-like ICL setups have been devised that train transformers on sequences of…

机器学习 · 计算机科学 2024-04-16 Madhur Panwar , Kabir Ahuja , Navin Goyal

Transformer models, notably large language models (LLMs), have the remarkable ability to perform in-context learning (ICL) -- to perform new tasks when prompted with unseen input-output examples without any explicit model training. In this…

机器学习 · 计算机科学 2023-11-03 Steve Yadlowsky , Lyric Doshi , Nilesh Tripuraneni

Transformers have demonstrated remarkable in-context learning (ICL) capabilities, adapting to new tasks by simply conditioning on demonstrations without parameter updates. Compelling empirical and theoretical evidence suggests that ICL, as…

机器学习 · 计算机科学 2025-10-28 Taejong Joo , Diego Klabjan

In-context learning (ICL) has emerged as a powerful capability of large pretrained transformers, enabling them to solve new tasks implicit in example input-output pairs without any gradient updates. Despite its practical success, the…

机器学习 · 计算机科学 2025-07-15 Joshua Hill , Benjamin Eyre , Elliot Creager

Predicting simple function classes has been widely used as a testbed for developing theory and understanding of the trained Transformer's in-context learning (ICL) ability. In this paper, we revisit the training of Transformers on linear…

机器学习 · 计算机科学 2024-05-27 Shang Liu , Zhongze Cai , Guanting Chen , Xiaocheng Li

Neural sequence models based on the transformer architecture have demonstrated remarkable \emph{in-context learning} (ICL) abilities, where they can perform new tasks when prompted with training and test examples, without any parameter…

机器学习 · 计算机科学 2023-07-07 Yu Bai , Fan Chen , Huan Wang , Caiming Xiong , Song Mei

In-context learning (ICL) of large language models has proven to be a surprisingly effective method of learning a new task from only a few demonstrative examples. In this paper, we study the efficacy of ICL from the viewpoint of statistical…

机器学习 · 统计学 2024-10-03 Juno Kim , Tai Nakamaki , Taiji Suzuki

In-context learning (ICL) is a central capability of Transformer models, but the structures in data that enable its emergence and govern its robustness remain poorly understood. In this work, we study how the structure of pretraining tasks…

机器学习 · 统计学 2025-10-01 Mary I. Letey , Jacob A. Zavatone-Veth , Yue M. Lu , Cengiz Pehlevan

Large language models (LLMs) have initiated a paradigm shift in transfer learning. In contrast to the classic pretraining-then-finetuning procedure, in order to use LLMs for downstream prediction tasks, one only needs to provide a few…

计算与语言 · 计算机科学 2025-09-16 Chi Han , Ziqi Wang , Han Zhao , Heng Ji

Transformer neural networks can exhibit a surprising capacity for in-context learning (ICL) despite not being explicitly trained for it. Prior work has provided a deeper understanding of how ICL emerges in transformers, e.g. through the…

机器学习 · 计算机科学 2023-12-13 Aaditya K. Singh , Stephanie C. Y. Chan , Ted Moskovitz , Erin Grant , Andrew M. Saxe , Felix Hill

The emergence of in-context learning (ICL) in large language models (LLMs) remains poorly understood despite its consistent effectiveness, enabling models to adapt to new tasks from only a handful of examples. To clarify and improve these…

机器学习 · 计算机科学 2025-10-02 Waïss Azizian , Ali Hasan

Transformers exhibit In-Context Learning (ICL), where these models solve new tasks by using examples in the prompt without additional training. In our work, we identify and analyze two key components of ICL: (1) context-scaling, where model…

机器学习 · 计算机科学 2024-10-17 Amirhesam Abedsoltan , Adityanarayanan Radhakrishnan , Jingfeng Wu , Mikhail Belkin

Transformers have shown a remarkable ability for in-context learning (ICL), making predictions based on contextual examples. However, while theoretical analyses have explored this prediction capability, the nature of the inferred context…

机器学习 · 计算机科学 2025-05-20 Fei Lu , Yue Yu

The transformer architecture, which processes sequences of input tokens to produce outputs for query tokens, has revolutionized numerous areas of machine learning. A defining feature of transformers is their ability to perform previously…

机器学习 · 计算机科学 2025-10-02 Hongbo Li , Lingjie Duan , Yingbin Liang

Transformers have a remarkable ability to learn and execute tasks based on examples provided within the input itself, without explicit prior training. It has been argued that this capability, known as in-context learning (ICL), is a…

机器学习 · 统计学 2025-10-06 Yue M. Lu , Mary I. Letey , Jacob A. Zavatone-Veth , Anindita Maiti , Cengiz Pehlevan

Transformer-based large language models have displayed impressive in-context learning capabilities, where a pre-trained model can handle new tasks without fine-tuning by simply augmenting the query with some input-output examples from that…

机器学习 · 计算机科学 2024-06-18 Hongkang Li , Meng Wang , Songtao Lu , Xiaodong Cui , Pin-Yu Chen

Transformers have emerged as the dominant architecture in the field of deep learning, with a broad range of applications and remarkable in-context learning (ICL) capabilities. While not yet fully understood, ICL has already proved to be an…

机器学习 · 计算机科学 2025-08-08 Arik Reuter , Tim G. J. Rudner , Vincent Fortuin , David Rügamer

In this paper, we conduct a comprehensive study of In-Context Learning (ICL) by addressing several open questions: (a) What type of ICL estimator is learned by large language models? (b) What is a proper performance metric for ICL and what…

机器学习 · 统计学 2023-10-11 Yufeng Zhang , Fengzhuo Zhang , Zhuoran Yang , Zhaoran Wang
‹ 上一页 1 2 3 10 下一页 ›