English
Related papers

Related papers: Adversarial Testing as a Tool for Interpretability…

200 papers

Transformer-based sequence-to-sequence architectures, while achieving state-of-the-art results on a large number of NLP tasks, can still suffer from overfitting during training. In practice, this is usually countered either by applying…

Computation and Language · Computer Science 2022-01-04 Dušan Variš , Ondřej Bojar

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

Length generalization, defined as the ability to extrapolate from shorter training sequences to longer test ones, is a significant challenge for language models. This issue persists even with large-scale Transformers handling relatively…

Machine Learning · Computer Science 2024-02-15 Yongchao Zhou , Uri Alon , Xinyun Chen , Xuezhi Wang , Rishabh Agarwal , Denny Zhou

We conduct a systematic study of the approximation properties of Transformer for sequence modeling with long, sparse and complicated memory. We investigate the mechanisms through which different components of Transformer, such as the…

Machine Learning · Computer Science 2024-10-31 Mingze Wang , Weinan E

The usage of transformers has grown from learning about language semantics to forming meaningful visiolinguistic representations. These architectures are often over-parametrized, requiring large amounts of computation. In this work, we…

Computation and Language · Computer Science 2020-07-09 Prajjwal Bhargava

Transformers have theoretical limitations in modeling certain sequence-to-sequence tasks, yet it remains largely unclear if these limitations play a role in large-scale pretrained LLMs, or whether LLMs might effectively overcome these…

Machine Learning · Computer Science 2025-10-24 Mayank Jobanputra , Yana Veitsman , Yash Sarrof , Aleksandra Bakalova , Vera Demberg , Ellie Pavlick , Michael Hahn

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

Increasing the input length has been a driver of progress in language modeling with transformers. We identify conditions where shorter inputs are not harmful, and achieve perplexity and efficiency improvements through two new methods that…

Computation and Language · Computer Science 2021-06-04 Ofir Press , Noah A. Smith , Mike Lewis

Adversarial training is a popular method to robustify models against adversarial attacks. However, it exhibits much more severe overfitting than training on clean inputs. In this work, we investigate this phenomenon from the perspective of…

Machine Learning · Computer Science 2024-12-18 Chen Liu , Zhichao Huang , Mathieu Salzmann , Tong Zhang , Sabine Süsstrunk

Standard adversarial training approaches suffer from robust overfitting where the robust accuracy decreases when models are adversarially trained for too long. The origin of this problem is still unclear and conflicting explanations have…

Machine Learning · Computer Science 2022-11-28 Muhammad Zaid Hameed , Beat Buesser

Transformers have supplanted recurrent models in a large number of NLP tasks. However, the differences in their abilities to model different syntactic properties remain largely unknown. Past works suggest that LSTMs generalize very well on…

Computation and Language · Computer Science 2020-10-09 Satwik Bhattamishra , Kabir Ahuja , Navin Goyal

Transformer becomes the state-of-the-art translation model, while it is not well studied how each intermediate component contributes to the model performance, which poses significant challenges for designing optimal architectures. In this…

Computation and Language · Computer Science 2020-11-10 Wenxuan Wang , Zhaopeng Tu

The long-distance agreement, evidence for syntactic structure, is increasingly used to assess the syntactic generalization of Neural Language Models. Much work has shown that transformers are capable of high accuracy in varied agreement…

Computation and Language · Computer Science 2023-01-05 Bingzhi Li , Guillaume Wisniewski , Benoît Crabbé

Adversarial training has been empirically shown to be more prone to overfitting than standard training. The exact underlying reasons still need to be fully understood. In this paper, we identify one cause of overfitting related to current…

Machine Learning · Computer Science 2022-11-30 Enes Altinisik , Safa Messaoud , Husrev Taha Sencar , Sanjay Chawla

We study the problem of length generalization (LG) in transformers: the ability of a model trained on shorter sequences to maintain performance when evaluated on much longer, previously unseen inputs. Prior work by Huang et al. (2025)…

Machine Learning · Computer Science 2025-11-03 Zachary Izzo , Eshaan Nichani , Jason D. Lee

It is a widely known issue that Transformers, when trained on shorter sequences, fail to generalize robustly to longer ones at test time. This raises the question of whether Transformer models are real reasoning engines, despite their…

Machine Learning · Computer Science 2025-04-04 Ruining Li , Gabrijel Boduljak , Jensen , Zhou

Deep neural network-based image classification can be misled by adversarial examples with small and quasi-imperceptible perturbations. Furthermore, the adversarial examples created on one classification model can also fool another different…

Computer Vision and Pattern Recognition · Computer Science 2021-11-23 Jindong Gu , Hengshuang Zhao , Volker Tresp , Philip Torr

Recurrent neural networks are effective models to process sequences. However, they are unable to learn long-term dependencies because of their inherent sequential nature. As a solution, Vaswani et al. introduced the Transformer, a model…

Machine Learning · Computer Science 2023-03-28 Quentin Fournier , Gaétan Marceau Caron , Daniel Aloise

Overfitting and generalization is an important concept in Machine Learning as only models that generalize are interesting for general applications. Yet some students have trouble learning this important concept through lectures and…

Machine Learning · Computer Science 2022-09-08 Matias Valdenegro-Toro , Matthia Sabatelli

When trained on language data, do transformers learn some arbitrary computation that utilizes the full capacity of the architecture or do they learn a simpler, tree-like computation, hypothesized to underlie compositional meaning systems…

Computation and Language · Computer Science 2022-11-07 Shikhar Murty , Pratyusha Sharma , Jacob Andreas , Christopher D. Manning
‹ Prev 1 2 3 10 Next ›