English
Related papers

Related papers: Emergence of Minimal Circuits for Indirect Object …

200 papers

Induction head mechanism is a part of the computational circuits for in-context learning (ICL) that enable large language models (LLMs) to adapt to new tasks without fine-tuning. Most existing work explains the training dynamics behind…

Computation and Language · Computer Science 2025-07-09 Shuo Wang , Issei Sato

The transformer architecture is widely used in machine learning models and consists of two alternating sublayers: attention heads and MLPs. We prove that an MLP neuron can be implemented by a masked attention head with internal dimension 1…

Machine Learning · Computer Science 2023-09-18 Robert Huben , Valerie Morris

The transformer has revolutionized modern AI across language, vision, and beyond. It consists of $L$ layers, each running $H$ attention heads in parallel and feeding the combined output to the subsequent layer. In attention, the input…

Computational Complexity · Computer Science 2026-03-13 Barna Saha , Yinzhan Xu , Christopher Ye , Hantao Yu

Transformer-based language models exhibit In-Context Learning (ICL), where predictions are made adaptively based on context. While prior work links induction heads to ICL through a sudden jump in accuracy, this can only account for ICL when…

Computation and Language · Computer Science 2025-06-11 Gouki Minegishi , Hiroki Furuta , Shohei Taniguchi , Yusuke Iwasawa , Yutaka Matsuo

Autoregressive decoder-only transformers have become key components for scalable sequence processing and generation models. However, the transformer's self-attention mechanism requires transferring prior token projections from the main…

Neural and Evolutionary Computing · Computer Science 2024-10-14 Jan Finkbeiner , Emre Neftci

Mechanistic interpretability has identified small sets of attention heads that implement specific behaviours in transformer language models, but recovering these circuits typically requires a bespoke analytical pipeline for each new task.…

Machine Learning · Computer Science 2026-05-27 Barsat Khadka

Despite the remarkable success of transformer-based models in various real-world tasks, their underlying mechanisms remain poorly understood. Recent studies have suggested that transformers can implement gradient descent as an in-context…

Machine Learning · Computer Science 2024-08-09 Xingwu Chen , Lei Zhao , Difan Zou

Transformers have become one of the dominant architectures in deep learning, particularly as a powerful alternative to convolutional neural networks (CNNs) in computer vision. However, Transformer training and inference in previous works…

Computer Vision and Pattern Recognition · Computer Science 2021-12-24 Zizheng Pan , Bohan Zhuang , Haoyu He , Jing Liu , Jianfei Cai

Language and vision-language models have shown impressive performance across a wide range of tasks, but their internal mechanisms remain only partly understood. In this work, we study how individual attention heads in text-generative models…

Computer Vision and Pattern Recognition · Computer Science 2026-01-15 Lorenzo Basile , Valentino Maiorca , Diego Doimo , Francesco Locatello , Alberto Cazzaniga

Attention layers are widely used in natural language processing (NLP) and are beginning to influence computer vision architectures. Training very large transformer models allowed significant improvement in both fields, but once trained,…

Machine Learning · Computer Science 2021-05-21 Jean-Baptiste Cordonnier , Andreas Loukas , Martin Jaggi

We study the problem of learning Transformer-based sequence models with black-box access to their outputs. In this setting, a learner may adaptively query the oracle with any sequence of vectors and observe the output of the target…

Machine Learning · Computer Science 2026-05-05 Satwik Bhattamishra , Kulin Shah , Michael Hahn , Varun Kanade

The Transformer is a sequence model that forgoes traditional recurrent architectures in favor of a fully attention-based approach. Besides improving performance, an advantage of using attention is that it can also help to interpret a model…

Human-Computer Interaction · Computer Science 2019-06-14 Jesse Vig

While explainable artificial intelligence (XAI) for large language models (LLMs) remains an evolving field with many unresolved questions, increasing regulatory pressures have spurred interest in its role in ensuring transparency,…

Machine Learning · Computer Science 2026-01-29 Viet Hung Dinh , Ming Ding , Youyang Qu , Kanchana Thilakarathna

We study the capabilities of the transformer architecture with varying depth. Specifically, we designed a novel set of sequence learning tasks to systematically evaluate and comprehend how the depth of transformer affects its ability to…

Machine Learning · Computer Science 2024-04-03 Xingwu Chen , Difan Zou

Large Language Models (LLMs) have shown impressive performance across a wide range of tasks. However, the size of LLMs is steadily increasing, hindering their application on computationally constrained environments. On the other hand,…

Machine Learning · Computer Science 2024-12-23 Jorge García-Carrasco , Alejandro Maté , Juan Trujillo

Despite the popularity of transformers in practice, their architectures are empirically designed and neither mathematically justified nor interpretable. Moreover, as indicated by many empirical studies, some components of transformer…

Machine Learning · Computer Science 2025-06-05 Peng Wang , Yifu Lu , Yaodong Yu , Druv Pai , Qing Qu , Yi Ma

The transformer architecture is central to the success of modern Large Language Models (LLMs), in part due to its surprising ability to perform a wide range of tasks - including mathematical reasoning, memorization, and retrieval - using…

Machine Learning · Computer Science 2025-09-05 Yihe Dong , Lorenzo Noci , Mikhail Khodak , Mufan Li

Transformer layers, which use an alternating pattern of multi-head attention and multi-layer perceptron (MLP) layers, provide an effective tool for a variety of machine learning problems. As the transformer layers use residual connections…

Machine Learning · Computer Science 2022-12-13 Yaofeng Desmond Zhong , Tongtao Zhang , Amit Chakraborty , Biswadip Dey

Transformer-based language models have achieved significant success; however, their internal mechanisms remain largely opaque due to the complexity of non-linear interactions and high-dimensional operations. While previous studies have…

Artificial Intelligence · Computer Science 2025-02-17 Lin Zhang , Lijie Hu , Di Wang

Many recent language models (LMs) of Transformers family exhibit so-called in-context learning (ICL) ability, manifested in the LMs' ability to modulate their function by a task described in a natural language input. Previous work curating…

Computation and Language · Computer Science 2023-05-24 Michal Štefánik , Marek Kadlčík