English
Related papers

Related papers: Towards Interpreting and Mitigating Shortcut Learn…

200 papers

Multi-modal Large Language Models (MLLMs) frequently face challenges from concept drift when dealing with real-world streaming data, wherein distributions change unpredictably. This mainly includes gradual drift due to long-tailed data and…

Computer Vision and Pattern Recognition · Computer Science 2025-02-18 Xiaoyu Yang , Jie Lu , En Yu

Real world data often have a long-tailed and open-ended distribution. A practical recognition system must classify among majority and minority classes, generalize from a few known instances, and acknowledge novelty upon a never seen…

Computer Vision and Pattern Recognition · Computer Science 2019-04-17 Ziwei Liu , Zhongqi Miao , Xiaohang Zhan , Jiayun Wang , Boqing Gong , Stella X. Yu

The emergence of Large Language Models (LLMs) with strong reasoning capabilities marks a significant milestone, unlocking new frontiers in complex problem-solving. However, training these reasoning models, typically using Reinforcement…

Machine Learning · Computer Science 2026-03-23 Qinghao Hu , Shang Yang , Junxian Guo , Xiaozhe Yao , Yujun Lin , Yuxian Gu , Han Cai , Chuang Gan , Ana Klimovic , Song Han

Debiasing language models from unwanted behaviors in Natural Language Understanding tasks is a topic with rapidly increasing interest in the NLP community. Spurious statistical correlations in the data allow models to perform shortcuts and…

Computation and Language · Computer Science 2022-12-06 Johannes Mario Meissner , Saku Sugawara , Akiko Aizawa

Object frequency in the real world often follows a power law, leading to a mismatch between datasets with long-tailed class distributions seen by a machine learning model and our expectation of the model to perform well on all classes. We…

Computer Vision and Pattern Recognition · Computer Science 2020-03-25 Muhammad Abdullah Jamal , Matthew Brown , Ming-Hsuan Yang , Liqiang Wang , Boqing Gong

The datasets used for Deep Neural Network training (e.g., ImageNet, MSCOCO, etc.) are often manually balanced across categories (classes) to facilitate learning of all the categories. This curation process is often expensive and requires…

Computer Vision and Pattern Recognition · Computer Science 2024-11-12 Harsh Rangwani

Shortcut learning refers to the phenomenon where models employ simple, non-robust decision rules in practical tasks, which hinders their generalization and robustness. With the rapid development of large language models (LLMs) in recent…

Computation and Language · Computer Science 2024-12-02 Rui Song , Yingji Li , Lida Shi , Fausto Giunchiglia , Hao Xu

Recent models for natural language understanding are inclined to exploit simple patterns in datasets, commonly known as shortcuts. These shortcuts hinge on spurious correlations between labels and latent features existing in the training…

Computation and Language · Computer Science 2024-11-19 Ukyo Honda , Tatsushi Oka , Peinan Zhang , Masato Mita

Long-tailed imbalance distribution is a common issue in practical computer vision applications. Previous works proposed methods to address this problem, which can be categorized into several classes: re-sampling, re-weighting, transfer…

Computer Vision and Pattern Recognition · Computer Science 2024-04-24 Pengxiao Han , Changkun Ye , Jieming Zhou , Jing Zhang , Jie Hong , Xuesong Li

Long-tailed data is still a big challenge for deep neural networks, even though they have achieved great success on balanced data. We observe that vanilla training on long-tailed data with cross-entropy loss makes the instance-rich head…

Computer Vision and Pattern Recognition · Computer Science 2023-05-22 Mengke Li , Yiu-ming Cheung , Yang Lu

In real-world data, long-tailed data distribution is common, making it challenging for models trained on empirical risk minimisation to learn and classify tail classes effectively. While many studies have sought to improve long tail…

Computer Vision and Pattern Recognition · Computer Science 2025-01-24 Ziheng Wang , Toni Lassila , Sharib Ali

Out-of-distribution (OOD) detection is crucial for deploying robust machine learning models. However, when training data follows a long-tailed distribution, the model's ability to accurately detect OOD samples is significantly compromised,…

Machine Learning · Computer Science 2025-09-26 Shuai Feng , Yuxin Ge , Yuntao Du , Mingcai Chen , Chongjun Wang , Lei Feng

In scenarios with long-tailed distributions, the model's ability to identify tail classes is limited due to the under-representation of tail samples. Class rebalancing, information augmentation, and other techniques have been proposed to…

Machine Learning · Computer Science 2023-10-17 Yanbiao Ma , Licheng Jiao , Fang Liu , Shuyuan Yang , Xu Liu , Lingling Li

In the recent past, a popular way of evaluating natural language understanding (NLU), was to consider a model's ability to perform natural language inference (NLI) tasks. In this paper, we investigate if NLI tasks, that are rarely used for…

Computation and Language · Computer Science 2024-11-22 Lovish Madaan , David Esiobu , Pontus Stenetorp , Barbara Plank , Dieuwke Hupkes

Several recent studies have shown that strong natural language understanding (NLU) models are prone to relying on unwanted dataset biases without learning the underlying task, resulting in models that fail to generalize to out-of-domain…

Computation and Language · Computer Science 2020-04-27 Rabeeh Karimi Mahabadi , Yonatan Belinkov , James Henderson

Neural machine learning models can successfully model language that is similar to their training distribution, but they are highly susceptible to degradation under distribution shift, which occurs in many practical applications when…

Machine Learning · Computer Science 2022-04-26 Antonio Valerio Miceli-Barone , Alexandra Birch , Rico Sennrich

Language models (LMs), despite their advances, often depend on spurious correlations, undermining their accuracy and generalizability. This study addresses the overlooked impact of subtler, more complex shortcuts that compromise model…

Computation and Language · Computer Science 2024-11-13 Yuqing Zhou , Ruixiang Tang , Ziyu Yao , Ziwei Zhu

Detecting out-of-distribution (OOD) data is essential for safe deployment of deep neural networks (DNNs). This problem becomes particularly challenging in the presence of long-tailed in-distribution (ID) datasets, often leading to high…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Nimeshika Udayangani , Hadi M. Dolatabadi , Sarah Erfani , Christopher Leckie

Real-world data usually present long-tailed distributions. Training on imbalanced data tends to render neural networks perform well on head classes while much worse on tail classes. The severe sparseness of training instances for the tail…

Machine Learning · Computer Science 2021-11-10 Chaozheng Wang , Shuzheng Gao , Cuiyun Gao , Pengyun Wang , Wenjie Pei , Lujia Pan , Zenglin Xu

We investigate the robustness of fine-tuned Large Language Models (LLMs) for the task of Natural Language Inference (NLI), finding that the in-distribution gains from fine-tuning correspond to a large drop in out-of-distribution (OOD)…

Computation and Language · Computer Science 2026-01-21 Joe Stacey , Lisa Alazraki , Aran Ubhi , Beyza Ermis , Aaron Mueller , Marek Rei