English
Related papers

Related papers: Transformers represent belief state geometry in th…

200 papers

Do transformers, when trained on sequential reasoning traces, build internal models of the underlying task? And if so, does the structure of those internal representations mirror the structure of the domain? We train an 8-layer transformer…

Machine Learning · Computer Science 2026-05-20 Roman Kniazev , Nathanaël Fijalkow

The internal representations learned by deep networks are often sensitive to architecture-specific choices, raising questions about the stability, alignment, and transferability of learned structure across models. In this paper, we…

Machine Learning · Computer Science 2025-08-06 Saleh Nikooroo , Thomas Engel

The transformer neural network has significantly out-shined all other neural network architectures as the engine behind large language models. We provide a theoretical analysis of the expressivity of the transformer architecture through the…

Machine Learning · Computer Science 2024-05-07 Mattia Jacopo Villani , Peter McBurney

The Transformer architecture has become prominent in developing large causal language models. However, mechanisms to explain its capabilities are not well understood. Focused on the training process, here we establish a meta-learning view…

Machine Learning · Computer Science 2024-03-26 Xinbo Wu , Lav R. Varshney

Transformers have proven highly effective across various applications, especially in handling sequential data such as natural languages and time series. However, transformer models often lack clear interpretability, and the success of…

Machine Learning · Computer Science 2025-12-01 Wei Shi , Yuan Cao

Deep Learning architectures, and in particular Transformers, are conventionally viewed as a composition of layers. These layers are actually often obtained as the sum of two contributions: a residual path that copies the input and the…

Pre-trained language models have been shown to encode linguistic structures, e.g. dependency and constituency parse trees, in their embeddings while being trained on unsupervised loss functions like masked language modeling. Some doubts…

Computation and Language · Computer Science 2023-10-17 Haoyu Zhao , Abhishek Panigrahi , Rong Ge , Sanjeev Arora

Transformers are the dominant architecture in AI, yet why they work remains poorly understood. This paper offers a precise answer: a transformer is a Bayesian network. We establish this in five ways. First, we prove that every sigmoid…

Artificial Intelligence · Computer Science 2026-03-19 Gregory Coppola

Many deep neural network architectures loosely based on brain networks have recently been shown to replicate neural firing patterns observed in the brain. One of the most exciting and promising novel architectures, the Transformer neural…

Neural and Evolutionary Computing · Computer Science 2022-03-16 James C. R. Whittington , Joseph Warren , Timothy E. J. Behrens

Transformer-based models generate hidden states that are difficult to interpret. In this work, we analyze hidden states and modify them at inference, with a focus on motion forecasting. We use linear probing to analyze whether interpretable…

Machine Learning · Computer Science 2025-05-19 Omer Sahin Tas , Royden Wagner

We investigate the relationship between the geometry of token embeddings and their role in the next token prediction within transformer models. An important aspect of this connection uses the notion of empirical measure, which encodes the…

Computation and Language · Computer Science 2025-01-22 Karthik Viswanathan , Yuri Gardinazzi , Giada Panerai , Alberto Cazzaniga , Matteo Biagetti

The transformer is a neural network component that can be used to learn useful representations of sequences or sets of data-points. The transformer has driven recent advances in natural language processing, computer vision, and…

Machine Learning · Computer Science 2026-01-21 Richard E. Turner

As artificial intelligence models have exploded in scale and capability, understanding of their internal mechanisms remains a critical challenge. Inspired by the success of dynamical systems approaches in neuroscience, here we propose a…

Artificial Intelligence · Computer Science 2025-02-18 Jesseba Fernando , Grigori Guitchounts

Network-structured data becomes ubiquitous in daily life and is growing at a rapid pace. It presents great challenges to feature engineering due to the high non-linearity and sparsity of the data. The local and global structure of the…

Machine Learning · Computer Science 2025-01-31 Xin Sun , Zenghui Song , Yongbo Yu , Junyu Dong , Claudia Plant , Christian Boehm

Transformers have become the foundational architecture for a broad spectrum of sequence modeling applications, underpinning state-of-the-art systems in natural language processing, vision, and beyond. However, their theoretical limitations…

Computation and Language · Computer Science 2026-02-13 Michelle Yuan , Weiyi Sun , Amir H. Rezaeian , Jyotika Singh , Sandip Ghoshal , Yao-Ting Wang , Miguel Ballesteros , Yassine Benajiba

Can we teach natural language understanding models to track their beliefs through intermediate points in text? We propose a representation learning framework called breakpoint modeling that allows for learning of this type. Given any text…

Computation and Language · Computer Science 2022-11-16 Kyle Richardson , Ronen Tamari , Oren Sultan , Reut Tsarfaty , Dafna Shahaf , Ashish Sabharwal

The Transformer architecture is shown to provide a powerful framework as an end-to-end model for building expression trees from online handwritten gestures corresponding to glyph strokes. In particular, the attention mechanism was…

Computation and Language · Computer Science 2022-11-07 Mirco Ramo , Guénolé C. M. Silvestre

Transformers demonstrate impressive performance on a range of reasoning benchmarks. To evaluate the degree to which these abilities are a result of actual reasoning, existing work has focused on developing sophisticated benchmarks for…

Machine Learning · Computer Science 2024-07-02 Jannik Brinkmann , Abhay Sheshadri , Victor Levoso , Paul Swoboda , Christian Bartelt

Transformers are widely used to extract semantic meanings from input tokens, yet they usually operate as black-box models. In this paper, we present a simple yet informative decomposition of hidden states (or embeddings) of trained…

Machine Learning · Computer Science 2024-02-06 Jiajun Song , Yiqiao Zhong

Modern deep neural networks display striking examples of rich internal computational structure. Uncovering principles governing the development of such structure is a priority for the science of deep learning. In this paper, we explore the…

Machine Learning · Computer Science 2025-02-03 Liam Carroll , Jesse Hoogland , Matthew Farrugia-Roberts , Daniel Murfet