English
Related papers

Related papers: Towards Interpreting and Mitigating Shortcut Learn…

200 papers

Shortcut learning is a phenomenon where machine learning models prioritize learning simple, potentially misleading cues from data that do not generalize well beyond the training set. While existing research primarily investigates this in…

Image and Video Processing · Electrical Eng. & Systems 2024-06-28 Manxi Lin , Nina Weng , Kamil Mikolaj , Zahra Bashir , Morten Bo Søndergaard Svendsen , Martin Tolsgaard , Anders Nymark Christensen , Aasa Feragen

Machine unlearning aims to solve the problem of removing the influence of selected training examples from a learned model. Despite the increasing attention to this problem, it remains an open research question how to evaluate unlearning in…

Machine Learning · Computer Science 2024-11-08 Teodora Baluta , Pascal Lamblin , Daniel Tarlow , Fabian Pedregosa , Gintare Karolina Dziugaite

Long-tailed recognition suffers from a persistent head--tail trade-off: improving tail performance often degrades head accuracy and can increase training instability. Despite strong empirical results from re-weighting, decoupled training,…

Machine Learning · Computer Science 2026-05-26 Chang Chu , Qingyue Zhang , Shao-Lun Huang , Junxiong Zheng

Likelihood-based deep generative models (DGMs) have gained significant attention for their ability to approximate the distributions of high-dimensional data. However, these models lack a performance guarantee in assigning higher likelihood…

Machine Learning · Computer Science 2025-02-04 Behrooz Montazeran , Ullrich Köthe

Long-tail learning is the problem of learning under skewed label distributions, which pose a challenge for standard learners. Several recent approaches for the problem have proposed enforcing a suitable margin in logit space. Such…

Machine Learning · Computer Science 2022-04-29 Wittawat Jitkrittum , Aditya Krishna Menon , Ankit Singh Rawat , Sanjiv Kumar

Deep neural network models degrade significantly in the long-tailed data distribution, with the overall training data dominated by a small set of classes in the head, and the tail classes obtaining less training examples. Addressing the…

Computer Vision and Pattern Recognition · Computer Science 2026-01-23 Brainard Philemon Jagati , Jitendra Tembhurne , Harsh Goud , Rudra Pratap Singh , Chandrashekhar Meshram

Spoken language understanding (SLU) treats automatic speech recognition (ASR) and natural language understanding (NLU) as a unified task and usually suffers from data scarcity. We exploit an ASR and NLU joint training method based on meta…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-28 Yingying Gao , Junlan Feng , Chao Deng , Shilei Zhang

Neural networks are known to produce over-confident predictions on input images, even when these images are out-of-distribution (OOD) samples. This limits the applications of neural network models in real-world scenarios, where OOD samples…

Computer Vision and Pattern Recognition · Computer Science 2022-07-19 Ke Fan , Yikai Wang , Qian Yu , Da Li , Yanwei Fu

Recent works have proposed incorporating heavy-tailed (HT) noise into diffusion- and flow-based generative models, with the goals of better recovering the tails of target distributions and improving generative diversity. This motivation is…

Machine Learning · Computer Science 2026-05-14 Hamza Cherkaoui , Hélène Halconruy , Antonio Ocello

While the Large Language Models (LLMs) dominate a majority of language understanding tasks, previous work shows that some of these results are supported by modelling spurious correlations of training datasets. Authors commonly assess model…

Computation and Language · Computer Science 2024-02-07 Lukáš Mikula , Michal Štefánik , Marek Petrovič , Petr Sojka

Large language models (LLMs) can learn vast amounts of knowledge from diverse domains during pre-training. However, long-tail knowledge from specialized domains is often scarce and underrepresented, rarely appearing in the models'…

Computation and Language · Computer Science 2025-02-11 Shuyang Yu , Runxue Bao , Parminder Bhatia , Taha Kass-Hout , Jiayu Zhou , Cao Xiao

Natural language understanding (NLU) and Natural language generation (NLG) tasks hold a strong dual relationship, where NLU aims at predicting semantic labels based on natural language utterances and NLG does the opposite. The prior work…

Computation and Language · Computer Science 2020-10-16 Shang-Yu Su , Yung-Sung Chuang , Yun-Nung Chen

Recent research has shown that large language models rely on spurious correlations in the data for natural language understanding (NLU) tasks. In this work, we aim to answer the following research question: Can we reduce spurious…

Computation and Language · Computer Science 2023-09-19 Zirui He , Huiqi Deng , Haiyan Zhao , Ninghao Liu , Mengnan Du

This paper proposes a new pipeline for long-tail (LT) recognition. Instead of re-weighting or re-sampling, we utilize the long-tailed dataset itself to generate a balanced proxy that can be optimized through cross-entropy (CE).…

Computer Vision and Pattern Recognition · Computer Science 2024-03-11 Jie Shao , Ke Zhu , Hanxiao Zhang , Jianxin Wu

We suggest a simple Gaussian mixture model for data generation that complies with Feldman's long tail theory (2020). We demonstrate that a linear classifier cannot decrease the generalization error below a certain level in the proposed…

Machine Learning · Computer Science 2023-07-26 Arman Bolatov , Maxat Tezekbayev , Igor Melnykov , Artur Pak , Vassilina Nikoulina , Zhenisbek Assylbekov

Models for natural language understanding (NLU) tasks often rely on the idiosyncratic biases of the dataset, which make them brittle against test cases outside the training distribution. Recently, several proposed debiasing methods are…

Computation and Language · Computer Science 2020-05-04 Prasetya Ajie Utama , Nafise Sadat Moosavi , Iryna Gurevych

In this study, we revisit the commonly-cited off-target issue in multilingual neural machine translation (MNMT). By carefully designing experiments on different MNMT scenarios and models, we attribute the off-target issue to the overfitting…

Computation and Language · Computer Science 2024-11-19 Wenxuan Wang , Wenxiang Jiao , Jen-tse Huang , Zhaopeng Tu , Michael R. Lyu

Children learn to speak with a low amount of data and can be taught new words on a few-shot basis, making them particularly data-efficient learners. The BabyLM challenge aims at exploring language model (LM) training in the low-data regime…

One of the most profound challenges of modern machine learning is performing well on the long-tail of rare and underrepresented features. Large general-purpose models are trained for many tasks, but work best on high-frequency use cases.…

Computation and Language · Computer Science 2025-06-18 Daniel D'souza , Julia Kreutzer , Adrien Morisot , Ahmet Üstün , Sara Hooker

Real-world visual data often exhibits a long-tailed distribution, where some ''head'' classes have a large number of samples, yet only a few samples are available for ''tail'' classes. Such imbalanced distribution causes a great challenge…

Computer Vision and Pattern Recognition · Computer Science 2020-03-11 Junjie Zhang , Lingqiao Liu , Peng Wang , Chunhua Shen