English
Related papers

Related papers: Arbitrary-Length Generalization for Addition in a …

200 papers

A recent study showed that large language models (LLMs) can reconstruct surprisingly long texts - up to thousands of tokens - via autoregressive generation from just one trained input embedding. In this work, we explore whether…

Computation and Language · Computer Science 2025-11-04 Gleb Mezentsev , Ivan Oseledets

In this paper, we describe ALTER, an auxiliary text rewriting tool that facilitates the rewriting process for natural language generation tasks, such as paraphrasing, text simplification, fairness-aware text rewriting, and text style…

Computation and Language · Computer Science 2019-09-17 Qiongkai Xu , Chenchen Xu , Lizhen Qu

Data augmentation, the artificial creation of training data for machine learning by transformations, is a widely studied research field across machine learning disciplines. While it is useful for increasing a model's generalization…

Computation and Language · Computer Science 2022-09-09 Markus Bayer , Marc-André Kaufhold , Christian Reuter

Transformers suffer from the computational overhead of their quadratic dependence on the length of sequences processed. We present three methods, all adding an intermediate step between training and inference/generation, which extend the…

Machine Learning · Computer Science 2024-08-21 R. I. Cukier

Large Language Models are increasingly being used for various tasks including content generation and as chatbots. Despite their impressive performances in general tasks, LLMs need to be aligned when applying for domain specific tasks to…

Computation and Language · Computer Science 2023-08-02 S. S. Manathunga , Y. A. Illangasekara

Large language models (LLMs) present significant risks when used to generate non-factual content and spread disinformation at scale. Detecting such LLM-generated content is crucial, yet current detectors often struggle to generalize in…

Computation and Language · Computer Science 2025-02-18 Ran Li , Wei Hao , Weiliang Zhao , Junfeng Yang , Chengzhi Mao

Multi-digit addition is a clear probe of the computational power of large language models. To dissect the internal arithmetic processes in LLaMA-3-8B-Instruct, we combine linear probing with logit-lens inspection. Inspired by the…

Artificial Intelligence · Computer Science 2025-09-10 Yao Yan

Augmenting large language models (LLMs) with auxiliary tokens has emerged as a promising strategy for enhancing model performance. In this work, we introduce a lightweight method termed latent tokens; these are dummy tokens that may be…

Machine Learning · Computer Science 2025-05-20 Yuchang Sun , Yanxi Chen , Yaliang Li , Bolin Ding

Large Transformer models routinely achieve state-of-the-art results on a number of tasks but training these models can be prohibitively costly, especially on long sequences. We introduce two techniques to improve the efficiency of…

Machine Learning · Computer Science 2020-02-19 Nikita Kitaev , Łukasz Kaiser , Anselm Levskaya

Generative modeling of high-dimensional data is a key problem in machine learning. Successful approaches include latent variable models and autoregressive models. The complementary strengths of these approaches, to model global and local…

Computer Vision and Pattern Recognition · Computer Science 2019-04-19 Thomas Lucas , Jakob Verbeek

Conversational AI systems that rely on Large Language Models, like Transformers, have difficulty interweaving external data (like facts) with the language they generate. Vanilla Transformer architectures are not designed for answering…

Computation and Language · Computer Science 2024-03-01 Stephan Raaijmakers , Roos Bakker , Anita Cremers , Roy de Kleijn , Tom Kouwenhoven , Tessa Verhoef

We introduce RE-Adapt, an approach to fine-tuning large language models on new domains without degrading any pre-existing instruction-tuning. We reverse engineer an adapter which isolates what an instruction-tuned model has learned beyond…

Computation and Language · Computer Science 2024-05-27 William Fleshman , Benjamin Van Durme

Generalizing vision-based reinforcement learning (RL) agents to novel environments remains a difficult and open challenge. Current trends are to collect large-scale datasets or use data augmentation techniques to prevent overfitting and…

Machine Learning · Computer Science 2025-08-13 Sumeet Batra , Gaurav S. Sukhatme

Data augmentation is a popular pre-processing trick to improve generalization accuracy. It is believed that by processing augmented inputs in tandem with the original ones, the model learns a more robust set of features which are shared…

Machine Learning · Computer Science 2020-07-10 Vihari Piratla , Shiv Shankar

Data augmentation is an effective way to diversify corpora in machine translation, but previous methods may introduce semantic inconsistency between original and augmented data because of irreversible operations and random subword sampling…

Computation and Language · Computer Science 2025-02-21 Jiashu Yao , Heyan Huang , Zeming Liu , Yuhang Guo

Discrete transforms, such as the discrete Fourier transform, are widely used in machine learning to improve model performance by extracting meaningful features. However, with numerous transforms available, selecting an appropriate one often…

Machine Learning · Computer Science 2025-05-09 Gekko Budiutama , Shunsuke Daimon , Hirofumi Nishi , Yu-ichiro Matsushita

Checking infinite-state systems is frequently done by encoding infinite sets of states as regular languages. Computing such a regular representation of, say, the set of reachable states of a system requires acceleration techniques that can…

Logic in Computer Science · Computer Science 2009-09-29 Axel Legay , Pierre Wolper

Generative adversarial networks (GANs) typically require ample data for training in order to synthesize high-fidelity images. Recent studies have shown that training GANs with limited data remains formidable due to discriminator…

Computer Vision and Pattern Recognition · Computer Science 2021-11-15 Liming Jiang , Bo Dai , Wayne Wu , Chen Change Loy

A general method to produce uniformly distributed pseudorandom numbers with extended precision by combining two pseudorandom numbers with lower precision is proposed. In particular, this method can be used for pseudorandom number generation…

Mathematical Software · Computer Science 2014-05-13 Vadim Demchik , Alexey Gulov

Scarcity of training data is one of the prominent problems for deep networks which require large amounts data. Data augmentation is a widely used method to increase the number of training samples and their variations. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2020-12-10 Hilmi Kumdakcı , Cihan Öngün , Alptekin Temizel