English
Related papers

Related papers: Transformers know more than they can tell -- Learn…

200 papers

Understanding how Transformers work and how they process information is key to the theoretical and empirical advancement of these machines. In this work, we demonstrate the existence of two phenomena in Transformers, namely isolation and…

We introduce Modelizer - a novel framework that, given a black-box program, learns a model from its input/output behavior using neural machine translation algorithms. The resulting model mocks the original program: Given an input, the model…

Software Engineering · Computer Science 2025-03-18 Tural Mammadov , Dietrich Klakow , Alexander Koller , Andreas Zeller

The Transformer model has a tendency to overfit various aspects of the training data, such as the overall sequence length. We study elementary string edit functions using a defined set of error indicators to interpret the behaviour of the…

Machine Learning · Computer Science 2024-10-18 Patrik Zavoral , Dušan Variš , Ondřej Bojar

Identifying how much a model ${\widehat{p}}_{\theta}(Y|X)$ knows about the stochastic real-world process $p(Y|X)$ it was trained on is important to ensure it avoids producing incorrect or "hallucinated" answers or taking unsafe actions. But…

Machine Learning · Computer Science 2024-05-29 Daniel D. Johnson , Daniel Tarlow , David Duvenaud , Chris J. Maddison

Transformer-based language models have demonstrated impressive capabilities across a range of complex reasoning tasks. Prior theoretical work exploring the expressive power of transformers has shown that they can efficiently perform…

Machine Learning · Computer Science 2025-05-30 Zixuan Wang , Eshaan Nichani , Alberto Bietti , Alex Damian , Daniel Hsu , Jason D. Lee , Denny Wu

This work represents an in-depth study of the structural behavior of the Collatz sequences. We consider a finite arithmetic progression with a common difference is 2 and the number of terms in the sequence is equal to 2^n . After, we…

General Mathematics · Mathematics 2021-04-26 Raouf Rajab

Chain of thought is a natural inference-time method for increasing the computational power of transformer-based large language models (LLMs), but comes at the cost of sequential decoding. Are there more efficient alternatives to expand a…

Machine Learning · Computer Science 2025-11-07 William Merrill , Ashish Sabharwal

Sequence-to-sequence (seq2seq) learners are widely used, but we still have only limited knowledge about what inductive biases shape the way they generalize. We address that by investigating how popular seq2seq learners generalize in tasks…

Computation and Language · Computer Science 2021-03-30 Eugene Kharitonov , Rahma Chaabouni

Large language models fail at counting repeated tokens despite strong performance on broader reasoning benchmarks. These failures are commonly attributed to limitations in internal count tracking. We show this attribution is wrong. Linear…

Computation and Language · Computer Science 2026-05-12 Sohan Venkatesh

Length generalization is a key property of a learning algorithm that enables it to make correct predictions on inputs of any length, given finite training data. To provide such a guarantee, one needs to be able to compute a length…

Machine Learning · Computer Science 2026-03-04 Andy Yang , Pascal Bergsträßer , Georg Zetzsche , David Chiang , Anthony W. Lin

We show that a constant number of self-attention layers can efficiently simulate, and be simulated by, a constant number of communication rounds of Massively Parallel Computation. As a consequence, we show that logarithmic depth is…

Machine Learning · Computer Science 2024-02-15 Clayton Sanford , Daniel Hsu , Matus Telgarsky

The Transformer model has achieved state-of-the-art performance in many sequence modeling tasks. However, how to leverage model capacity with large or variable depths is still an open challenge. We present a probabilistic framework to…

Computation and Language · Computer Science 2020-10-19 Xian Li , Asa Cooper Stickland , Yuqing Tang , Xiang Kong

Sequence modelling requires determining which past tokens are causally relevant from the context and their importance: a process inherent to the attention layers in transformers, yet whose underlying learned mechanisms remain poorly…

Machine Learning · Computer Science 2026-04-14 Francesco D'Angelo , Nicolas Flammarion

Large language models are capable of in-context learning, the ability to perform new tasks at test time using a handful of input-output examples, without parameter updates. We develop a universal approximation theory to elucidate how…

Machine Learning · Computer Science 2025-08-29 Gen Li , Yuchen Jiao , Yu Huang , Yuting Wei , Yuxin Chen

Despite the remarkable practical success of transformer-based language models, recent work has raised concerns about their ability to perform state tracking. In particular, a growing body of literature has shown this limitation primarily…

Machine Learning · Computer Science 2026-02-23 M. Reza Ebrahimi , Michaël Defferrard , Sunny Panchal , Roland Memisevic

In this paper, we consider the supervised pre-trained transformer for a class of sequential decision-making problems. The class of considered problems is a subset of the general formulation of reinforcement learning in that there is no…

Machine Learning · Computer Science 2024-10-03 Hanzhao Wang , Yu Pan , Fupeng Sun , Shang Liu , Kalyan Talluri , Guanting Chen , Xiaocheng Li

In problem solving, understanding the problem that one seeks to solve is an essential initial step. In this paper, we propose computational methods for facilitating problem understanding through the task of recognizing the unknown in…

Computation and Language · Computer Science 2021-11-30 Ndapa Nakashole

The transformer-based pre-trained language models have been tremendously successful in most of the conventional NLP tasks. But they often struggle in those tasks where numerical understanding is required. Some possible reasons can be the…

Computation and Language · Computer Science 2021-09-13 Kuntal Kumar Pal , Chitta Baral

Classification algorithms using Transformer architectures can be affected by the sequence length learning problem whenever observations from different classes have a different length distribution. This problem causes models to use sequence…

Machine Learning · Computer Science 2024-03-15 Jean-Thomas Baillargeon , Luc Lamontagne

The incredible success of transformers on sequence modeling tasks can be largely attributed to the self-attention mechanism, which allows information to be transferred between different parts of a sequence. Self-attention allows…

Machine Learning · Computer Science 2024-08-14 Eshaan Nichani , Alex Damian , Jason D. Lee