English
Related papers

Related papers: Memorization in Attention-only Transformers

200 papers

Transformer is a powerful model for text understanding. However, it is inefficient due to its quadratic complexity to input sequence length. Although there are many methods on Transformer acceleration, they are still either inefficient on…

Computation and Language · Computer Science 2021-09-07 Chuhan Wu , Fangzhao Wu , Tao Qi , Yongfeng Huang , Xing Xie

Transformer-based language models (LMs) have achieved widespread empirical success, but their theoretical expressive power remains only partially understood. In this work, we analyze a restricted idealization of fixed-precision transformers…

Computation and Language · Computer Science 2025-12-04 Jiaoda Li , Ryan Cotterell

Transformers have achieved remarkable successes across a wide range of applications, yet the theoretical foundation of their model efficiency remains underexplored. In this work, we investigate how the model parameters -- mainly attention…

Machine Learning · Computer Science 2025-10-07 Ruoxi Yu , Haotian Jiang , Jingpu Cheng , Penghao Yu , Qianxiao Li , Zhong Li

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

Multi-head self-attention-based Transformers have shown promise in different learning tasks. Albeit these models exhibit significant improvement in understanding short-term and long-term contexts from sequences, encoders of Transformers and…

Computation and Language · Computer Science 2023-10-24 Ayan Sengupta , Md Shad Akhtar , Tanmoy Chakraborty

This paper introduces a novel approach to enhance the capabilities of Large Language Models (LLMs) in processing and understanding extensive text sequences, a critical aspect in applications requiring deep comprehension and synthesis of…

Computation and Language · Computer Science 2023-12-15 Kaiqiang Song , Xiaoyang Wang , Sangwoo Cho , Xiaoman Pan , Dong Yu

Attention layers -- which map a sequence of inputs to a sequence of outputs -- are core building blocks of the Transformer architecture which has achieved significant breakthroughs in modern artificial intelligence. This paper presents a…

Machine Learning · Computer Science 2023-07-24 Hengyu Fu , Tianyu Guo , Yu Bai , Song Mei

Large language models often expose their brittleness in reasoning tasks, especially while executing long chains of reasoning over context. We propose MemReasoner, a new and simple memory-augmented LLM architecture, in which the memory…

Computation and Language · Computer Science 2025-03-12 Payel Das , Ching-Yun Ko , Sihui Dai , Georgios Kollias , Subhajit Chaudhury , Aurelie Lozano

Recent progress has rapidly advanced our understanding of the mechanisms underlying in-context learning in modern attention-based neural networks. However, existing results focus exclusively on unimodal data; in contrast, the theoretical…

Machine Learning · Statistics 2026-05-19 Nicholas Barnfield , Subhabrata Sen , Pragya Sur

Modern foundation models such as large language models (LLMs) and large multi-modal models (LMMs) require a massive amount of computational and memory resources. We propose a new framework to convert such LLMs/LMMs into a reduced-dimension…

Machine Learning · Computer Science 2025-05-27 Toshiaki Koike-Akino , Xiangyu Chen , Jing Liu , Ye Wang , Pu , Wang , Matthew Brand

Transformer-based large language models (LLMs) excel in modeling complex language patterns but face significant computational costs during inference, especially with long inputs due to the attention mechanism's memory overhead. We observe…

Computation and Language · Computer Science 2024-10-18 Ruiqing Yan , Linghan Zheng , Xingbo Du , Han Zou , Yufeng Guo , Jianfei Yang

Large language models (LLMs) exhibit a wide range of capabilities, including mathematical reasoning, code generation, and linguistic behaviors. We show that many capabilities are highly localized to small subsets of attention heads within…

Computation and Language · Computer Science 2026-03-05 Anna Bair , Yixuan Even Xu , Mingjie Sun , J. Zico Kolter

Central to the success of Transformers is the attention block, which effectively models global dependencies among input tokens associated to a dataset. However, we theoretically demonstrate that standard attention mechanisms in transformers…

Machine Learning · Computer Science 2026-03-31 Hemanth Saratchandran

Self-attention model have shown its flexibility in parallel computation and the effectiveness on modeling both long- and short-term dependencies. However, it calculates the dependencies between representations without considering the…

Computation and Language · Computer Science 2019-02-18 Baosong Yang , Jian Li , Derek Wong , Lidia S. Chao , Xing Wang , Zhaopeng Tu

Document-level context for neural machine translation (NMT) is crucial to improve the translation consistency and cohesion, the translation of ambiguous inputs, as well as several other linguistic phenomena. Many works have been published…

Computation and Language · Computer Science 2023-06-09 Christian Herold , Hermann Ney

In both Computer Vision and the wider Deep Learning field, the Transformer architecture is well-established as state-of-the-art for many applications. For Multitask Learning, however, where there may be many more queries necessary compared…

Computer Vision and Pattern Recognition · Computer Science 2025-08-07 Christian Bohn , Thomas Kurbiel , Klaus Friedrichs , Hasan Tercan , Tobias Meisen

Psycholinguistic research suggests that humans may build a representation of linguistic input that is 'good-enough' for the task at hand. This study examines what architectural features make language models learn human-like good-enough…

Computation and Language · Computer Science 2024-06-07 Daiki Asami , Saku Sugawara

Numerous recent works target to extend effective context length for language models and various methods, tasks and benchmarks exist to measure model's effective memorization length. However, through thorough investigations, we find…

Computation and Language · Computer Science 2024-10-08 Xinyu Liu , Runsong Zhao , Pengcheng Huang , Chunyang Xiao , Bei Li , Jingang Wang , Tong Xiao , Jingbo Zhu

This paper studies how the model architecture and data configurations influence the empirical memorization capacity of generative transformers. The models are trained using synthetic text datasets derived from the Systematized Nomenclature…

Computation and Language · Computer Science 2025-06-18 Anton Changalidis , Aki Härmä

The Transformer-based models with the multi-head self-attention mechanism are widely used in natural language processing, and provide state-of-the-art results. While the pre-trained language backbones are shown to implicitly capture certain…

Computation and Language · Computer Science 2023-12-18 Zhengyuan Liu , Nancy F. Chen