Transformers can learn broad families of tasks during pretraining and adapt to unseen tasks from a short prompt, but a rigorous understanding of this capability is limited. This paper studies how shared cross‑task structure influences the sample complexity of in‑context learning (ICL) by characterizing task‑space complexity through covering numbers, yielding a set of anchor functions that localize unseen tasks and predict responses. The authors construct a Transformer with Softmax attention to approximate this procedure and derive an error bound that separates the effects of pretraining tasks and prompt length, showing that once enough tasks are available the dependence on prompt length becomes dimension‑free.
By Zhongjie Shi, Rongjie Lai, Alexander Cloninger, Wenjing Liao
arXiv:2607. 00479v1 Announce Type: new Abstract: Transformer-based large models have demonstrated remarkable generalization abilities across different tasks by leveraging a context-aware attention module for in-context learning.
By Peilin Liu, Ding-Xuan Zhou
arXiv:2510. 00399v2 Announce Type: replace Abstract: The Mamba model has gained significant attention for its computational advantages over Transformer-based models, while achieving comparable performance across a wide range of language tasks.
By Hongkang Li, Songtao Lu, Xiaodong Cui, Pin-Yu Chen, Meng Wang
arXiv:2509.18349v4 Announce Type: replace
Abstract: Meta-learning aims to leverage information across related tasks to improve prediction on unlabeled data for new tasks when only a small number of l...
By Saptati Datta, Nicolas W. Hengartner, Yulia Pimonova, Natalie E. Klein, Nicholas Lubbers
arXiv:2510. 10981v3 Announce Type: replace-cross Abstract: This paper develops a finite-sample statistical theory for in-context learning (ICL), analyzed within a meta-learning framework that accommodates mixtures of diverse task types.
By Tomoya Wakayama, Taiji Suzuki
arXiv:2510. 01163v2 Announce Type: replace Abstract: The factors driving the performance of in-context learning (ICL) in large language models (LLMs) remain poorly understood despite ICL's surprising effectiveness, enabling models to adapt to new tasks from only a handful of examples.
By Wa\"iss Azizian, Ali Hasan
arXiv:2312. 06173v2 Announce Type: replace Abstract: Merging models fine-tuned from a common, extensively pre-trained large model but specialized for different tasks has been demonstrated as a cheap and scalable strategy to construct a multi-task model that performs well across diverse tasks.
By Anke Tang, Xianglin Luo, Li Shen, Yong Luo, Liang Ding, Han Hu, Bo Du, Dacheng Tao
arXiv:2606. 16694v1 Announce Type: cross Abstract: Transformers are widely used as a general-purpose substrate for learning complex correlations between a large collection of coupled variables, but their internal mechanisms have remained mysterious.
By Ravin Raj, Gautam Reddy
arXiv:2609.31458v1 Announce Type: new
Abstract: Transformers have become a central architecture for in-context learning (ICL), particularly through their state-of-the-art performance in large languag...
By Jaehee Seo, Jisu Kim
arXiv:2605. 28854v2 Announce Type: replace-cross Abstract: Large language models (LLMs) exhibit remarkable flexibility in adapting to novel tasks from in-context examples without parameter updates, a capability known as in-context learning (ICL).
By Hua-Dong Xiong, Li Ji-An, Robert C. Wilson, Kwonjoon Lee, Xue-Xin Wei
The paper investigates how transformer language models perform few‑shot learning for a simple addition task, showing that the ability is concentrated in a handful of attention heads. Using dimensionality reduction, the authors identify low‑dimensional subspaces—three heads with six‑dimensional spaces in Llama‑3‑8B‑Instruct—where specific dimensions encode the units digit via trigonometric patterns and magnitude via low‑frequency components. They also derive a mathematical identity linking aggregator and extractor subspaces, enabling tracking of information flow from examples to the final prediction.
By Xinyan Hu, Kayo Yin, Michael I. Jordan, Jacob Steinhardt, Lijie Chen
arXiv:2606. 05134v1 Announce Type: cross Abstract: Deep active learning has previously been explored for LLM in-context sample selection, but not with methods that utilise recent advances in understanding of transformer activations.
By Yaseen M. Osman, Geoff V. Merrett, Stuart E. Middleton