English
Related papers

Related papers: Positional Description Matters for Transformers Ar…

200 papers

Transformers are arguably the main workhorse in recent Natural Language Processing research. By definition a Transformer is invariant with respect to reordering of the input. However, language is inherently sequential and word order is…

Computation and Language · Computer Science 2021-09-10 Philipp Dufter , Martin Schmitt , Hinrich Schütze

We present a Positional Description Scheme (PDS) tailored for digit sequences, integrating placeholder value information for each digit. Given the structural limitations of subword tokenization algorithms, language models encounter critical…

Computation and Language · Computer Science 2024-08-23 Deepanshu Gupta , Javier Latorre

It has been observed in recent years that transformers have problems with length generalization for certain types of reasoning and arithmetic tasks. In particular, the performance of a transformer model trained on tasks (say addition) up to…

Machine Learning · Computer Science 2023-10-03 Pranjal Awasthi , Anupam Gupta

The Transformer based neural networks have been showing significant advantages on most evaluations of various natural language processing and other sequence-to-sequence tasks due to its inherent architecture based superiorities. Although…

Computation and Language · Computer Science 2019-10-31 Hailiang Li , Adele Y. C. Wang , Yang Liu , Du Tang , Zhibin Lei , Wenye Li

Position modeling plays a critical role in Transformers. In this paper, we focus on length extrapolation, i.e., training on short texts while evaluating longer sequences. We define attention resolution as an indicator of extrapolation. Then…

Computation and Language · Computer Science 2022-12-21 Yutao Sun , Li Dong , Barun Patra , Shuming Ma , Shaohan Huang , Alon Benhaim , Vishrav Chaudhary , Xia Song , Furu Wei

There is a growing interest in the ability of neural networks to execute algorithmic tasks (e.g., arithmetic, summary statistics, and sorting). The goal of this work is to better understand the role of attention in Transformers for…

Machine Learning · Computer Science 2025-06-11 Artur Back de Luca , George Giapitzakis , Shenghao Yang , Petar Veličković , Kimon Fountoulakis

A key module in neural transformer-based deep architectures is positional encoding. This module enables a suitable way to encode positional information as input for transformer neural layers. This success has been rooted in the use of…

Machine Learning · Computer Science 2025-12-23 Ezequiel Lopez-Rubio , Macoris Decena-Gimenez , Rafael Marcos Luque-Baena

Modular exponentiation is crucial to number theory and cryptography, yet remains largely unexplored from a mechanistic interpretability standpoint. We train a 4-layer encoder-decoder Transformer model to perform this operation and…

Machine Learning · Computer Science 2025-10-24 David Demitri Africa , Sara M. Kapoor , Theo Simon Sorg , Challenger Mishra

Recurrent models have been dominating the field of neural machine translation (NMT) for the past few years. Transformers \citep{vaswani2017attention}, have radically changed it by proposing a novel architecture that relies on a feed-forward…

Computation and Language · Computer Science 2022-10-25 Joyce Zheng , Mehdi Rezagholizadeh , Peyman Passban

Machine learning has become a promising approach for molecular modeling. Positional quantities, such as interatomic distances and bond angles, play a crucial role in molecule physics. The existing works rely on careful manual design of…

Machine Learning · Computer Science 2022-11-24 Xiang Gao , Weihao Gao , Wenzhi Xiao , Zhirui Wang , Chong Wang , Liang Xiang

We introduce a new way of learning to encode position information for non-recurrent models, such as Transformer models. Unlike RNN and LSTM, which contain inductive bias by loading the input tokens sequentially, non-recurrent models are…

Machine Learning · Computer Science 2020-03-23 Xuanqing Liu , Hsiang-Fu Yu , Inderjit Dhillon , Cho-Jui Hsieh

In recent years, pre-trained Transformers have dominated the majority of NLP benchmark tasks. Many variants of pre-trained Transformers have kept breaking out, and most focus on designing different pre-training objectives or variants of…

Computation and Language · Computer Science 2020-10-13 Yu-An Wang , Yun-Nung Chen

Positional encodings are a core part of transformer-based models, enabling processing of sequential data without recurrence. This paper presents a theoretical framework to analyze how various positional encoding methods, including…

Machine Learning · Computer Science 2025-06-10 Yin Li

Transformer-based models excel in various tasks but their generalization capabilities, especially in arithmetic reasoning, remain incompletely understood. Arithmetic tasks provide a controlled framework to explore these capabilities, yet…

Machine Learning · Computer Science 2025-08-07 Xingcheng Xu , Zibo Zhao , Haipeng Zhang , Yanqing Yang

Accurately estimating the pose of an object is a crucial task in computer vision and robotics. There are two main deep learning approaches for this: geometric representation regression and iterative refinement. However, these methods have…

Computer Vision and Pattern Recognition · Computer Science 2024-01-30 Jaewoo Park , Jaeguk Kim , Nam Ik Cho

Transformer network architecture has proven effective in speech enhancement. However, as its core module, self-attention suffers from quadratic complexity, making it infeasible for training on long speech utterances. In practical scenarios,…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-10 Qiquan Zhang , Hongxu Zhu , Xinyuan Qian , Eliathamby Ambikairajah , Haizhou Li

Transformer-based models have demonstrated state-of-the-art performance in many intelligent coding tasks such as code comment generation and code completion. Previous studies show that deep learning models are sensitive to the input…

Software Engineering · Computer Science 2025-06-10 Yaoxian Li , Shiyi Qi , Cuiyun Gao , Yun Peng , David Lo , Zenglin Xu , Michael R. Lyu

Graph Transformers, which incorporate self-attention and positional encoding, have recently emerged as a powerful architecture for various graph learning tasks. Despite their impressive performance, the complex non-convex interactions…

Machine Learning · Computer Science 2024-06-05 Hongkang Li , Meng Wang , Tengfei Ma , Sijia Liu , Zaixi Zhang , Pin-Yu Chen

We examine how transformers cope with two challenges: learning basic integer arithmetic, and generalizing to longer sequences than seen during training. We find that relative position embeddings enable length generalization for simple…

Machine Learning · Computer Science 2023-06-28 Samy Jelassi , Stéphane d'Ascoli , Carles Domingo-Enrich , Yuhuai Wu , Yuanzhi Li , François Charton

A major challenge for transformers is generalizing to sequences longer than those observed during training. While previous works have empirically shown that transformers can either succeed or fail at length generalization depending on the…

Machine Learning · Computer Science 2025-05-01 Xinting Huang , Andy Yang , Satwik Bhattamishra , Yash Sarrof , Andreas Krebs , Hattie Zhou , Preetum Nakkiran , Michael Hahn