English
Related papers

Related papers: Quantifying LLM Attention-Head Stability: Implicat…

200 papers

Transformer has become the dominant architecture for sequence modeling, yet a detailed understanding of how its structural parameters influence expressive power remains limited. In this work, we study the approximation properties of…

Machine Learning · Computer Science 2026-04-01 Penghao Yu , Haotian Jiang , Zeyu Bao , Ruoxi Yu , Qianxiao Li

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

We study how multi-head softmax attention models are trained to perform in-context learning on linear data. Through extensive empirical experiments and rigorous theoretical analysis, we demystify the emergence of elegant attention patterns:…

Machine Learning · Computer Science 2025-05-29 Jianliang He , Xintian Pan , Siyu Chen , Zhuoran Yang

Attention layers, as commonly used in transformers, form the backbone of modern deep learning, yet there is no mathematical description of their benefits and deficiencies as compared with other architectures. In this work we establish both…

Machine Learning · Computer Science 2023-11-17 Clayton Sanford , Daniel Hsu , Matus Telgarsky

Large language models (LLMs) reliably predict neural activity during language comprehension and transformer depth has been interpreted as mirroring hierarchical cortical organization. However, it remains unclear whether such alignment…

Computation and Language · Computer Science 2026-05-21 Ni Yang , Rui He , Philipp Homan , Iris Sommer , Davide Staub , Wolfram Hinzen

Looped transformers promise test-time compute scaling by spending more iterations on harder problems, but it remains unclear which architectural choices let them extrapolate to harder problems at test time rather than memorize…

Machine Learning · Computer Science 2026-04-23 Asher Labovich

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

Transformer language models have driven significant progress across various fields, including natural language processing and computer vision. A central component of these models is the self-attention (SA) mechanism, which learns rich…

Machine Learning · Computer Science 2025-05-22 Suvadeep Hajra

The transformer architecture has become the foundation of modern Large Language Models (LLMs), yet its theoretical properties are still not well understood. As with classic neural networks, a common approach to improve these models is to…

Artificial Intelligence · Computer Science 2025-09-26 Álvaro Rodríguez Abella , João Pedro Silvestre , Paulo Tabuada

Despite their widespread use, training deep Transformers can be unstable. Layer normalization, a standard component, improves training stability, but its placement has often been ad-hoc. In this paper, we conduct a principled study on the…

Machine Learning · Computer Science 2025-10-14 Kelvin Kan , Xingjian Li , Benjamin J. Zhang , Tuhin Sahai , Stanley Osher , Krishna Kumar , Markos A. Katsoulakis

The robustness of neural networks against input perturbations with bounded magnitude represents a serious concern in the deployment of deep learning models in safety-critical systems. Recently, the scientific community has focused on…

Machine Learning · Computer Science 2023-11-29 Bernd Prach , Fabio Brau , Giorgio Buttazzo , Christoph H. Lampert

Transformer models have been widely adopted in various domains over the last years, and especially large language models have advanced the field of AI significantly. Due to their size, the capability of these networks has increased…

Machine Learning · Computer Science 2023-11-10 Yelysei Bondarenko , Markus Nagel , Tijmen Blankevoort

Large Language Models (LLMs) and transformer architectures have shown impressive reasoning and generation capabilities across diverse natural language tasks. However, their reliability and robustness in real-world engineering domains remain…

Machine Learning · Computer Science 2025-12-11 Yasaman Esfandiari , Jocelyn Rego , Austin Meyer , Jonathan Gallagher , Mia Levy

Transformer language models contain localized reasoning circuits, contiguous layer blocks that improve reasoning when duplicated at inference time. Finding these circuits currently requires brute-force sweeps costing 25 GPU hours per model.…

Artificial Intelligence · Computer Science 2026-04-02 Rajkiran Panuganti

The neocortex has a remarkably uniform neuronal organization, suggesting that common principles of processing are employed throughout its extent. In particular, the patterns of connectivity observed in the superficial layers of the visual…

Neurons and Cognition · Quantitative Biology 2011-05-17 Ueli Rutishauser , Rodney J. Douglas , Jean-Jacques Slotine

Transformers have become a standard neural network architecture for many NLP problems, motivating theoretical analysis of their power in terms of formal languages. Recent work has shown that transformers with hard attention are quite…

Computation and Language · Computer Science 2022-04-12 William Merrill , Ashish Sabharwal , Noah A. Smith

Large Language Models (LLMs), already shown to ace various unstructured text comprehension tasks, have also remarkably been shown to tackle table (structured) comprehension tasks without specific training. Building on earlier studies of…

Computation and Language · Computer Science 2025-08-27 Kushal Raj Bhandari , Sixue Xing , Soham Dan , Jianxi Gao

As machine learning systems are increasingly used in high-stakes domains, there is a growing emphasis placed on making them interpretable to improve trust in these systems. In response, a range of interpretable machine learning (IML)…

Machine Learning · Statistics 2025-05-22 Luqin Gan , Tarek M. Zikry , Genevera I. Allen

Large language models (LLMs) exhibit impressive fluency, but often produce critical errors known as "hallucinations". Uncertainty quantification (UQ) methods are a promising tool for coping with this fundamental shortcoming. Yet, existing…

The intriguing in-context learning (ICL) abilities of deep Transformer models have lately garnered significant attention. By studying in-context linear regression on unimodal Gaussian data, recent empirical and theoretical works have argued…

Machine Learning · Computer Science 2024-10-30 Khashayar Gatmiry , Nikunj Saunshi , Sashank J. Reddi , Stefanie Jegelka , Sanjiv Kumar