English
Related papers

Related papers: CausalAPM: Generalizable Literal Disentanglement f…

200 papers

Large Language Models (LLMs) are known to exhibit social, demographic, and gender biases, often as a consequence of the data on which they are trained. In this work, we adopt a mechanistic interpretability approach to analyze how such…

Computation and Language · Computer Science 2025-06-09 Bhavik Chandna , Zubair Bashir , Procheta Sen

Existing NLP datasets contain various biases that models can easily exploit to achieve high performances on the corresponding evaluation sets. However, focusing on dataset-specific biases limits their ability to learn more generalizable…

Computation and Language · Computer Science 2020-10-08 Mingzhu Wu , Nafise Sadat Moosavi , Andreas Rücklé , Iryna Gurevych

Natural Language Sentence Matching (NLSM) has gained substantial attention from both academics and the industry, and rich public datasets contribute a lot to this process. However, biased datasets can also hurt the generalization…

Computation and Language · Computer Science 2019-06-11 Guanhua Zhang , Bing Bai , Jian Liang , Kun Bai , Shiyu Chang , Mo Yu , Conghui Zhu , Tiejun Zhao

The recent increase in dataset size has brought about significant advances in natural language understanding. These large datasets are usually collected through automation (search engines or web crawlers) or crowdsourcing which inherently…

Computation and Language · Computer Science 2021-09-21 Arka Talukdar , Monika Dagar , Prachi Gupta , Varun Menon

NLP models often rely on superficial cues known as dataset biases to achieve impressive performance, and can fail on examples where these biases do not hold. Recent work sought to develop robust, unbiased models by filtering biased examples…

Computation and Language · Computer Science 2023-05-31 Yuval Reif , Roy Schwartz

There have been growing concerns around high-stake applications that rely on models trained with biased data, which consequently produce biased predictions, often harming the most vulnerable. In particular, biased medical data could cause…

Computation and Language · Computer Science 2024-09-12 Gavin Butts , Pegah Emdad , Jethro Lee , Shannon Song , Chiman Salavati , Willmar Sosa Diaz , Shiri Dori-Hacohen , Fabricio Murai

In this paper, we study the "dataset bias" problem from a statistical standpoint, and identify the main cause of the problem as the strong correlation between a class attribute u and a non-class attribute b in the input x, represented by…

Machine Learning · Computer Science 2024-02-07 Kien Do , Dung Nguyen , Hung Le , Thao Le , Dang Nguyen , Haripriya Harikumar , Truyen Tran , Santu Rana , Svetha Venkatesh

Causal disentanglement aims to learn about latent causal factors behind data, holding the promise to augment existing representation learning methods in terms of interpretability and extrapolation. Recent advances establish identifiability…

Machine Learning · Computer Science 2024-12-25 Ryan Welch , Jiaqi Zhang , Caroline Uhler

Large amounts of training data are one of the major reasons for the high performance of state-of-the-art NLP models. But what exactly in the training data causes a model to make a certain prediction? We seek to answer this question by…

While deep learning models are making fast progress on the task of Natural Language Inference, recent studies have also shown that these models achieve high accuracy by exploiting several dataset biases, and without deep understanding of…

Computation and Language · Computer Science 2020-05-15 Xiang Zhou , Mohit Bansal

Machine learning model bias can arise from dataset composition: correlated sensitive features can distort the downstream classification model's decision boundary and lead to performance differences along these features. Existing de-biasing…

Computer Vision and Pattern Recognition · Computer Science 2025-01-22 Miao Zhang , Zee fryer , Ben Colman , Ali Shahriyari , Gaurav Bharaj

Model robustness to bias is often determined by the generalization on carefully designed out-of-distribution datasets. Recent debiasing methods in natural language understanding (NLU) improve performance on such datasets by pressuring…

Computation and Language · Computer Science 2021-09-10 Michael Mendelson , Yonatan Belinkov

Machine unlearning requires removing the information of forgetting data while keeping the necessary information of remaining data. Despite recent advancements in this area, existing methodologies mainly focus on the effect of removing…

Machine Learning · Computer Science 2024-02-01 Shaofei Shen , Chenhao Zhang , Alina Bialkowski , Weitong Chen , Miao Xu

The ability to learn disentangled representations that split underlying sources of variation in high dimensional, unstructured data is important for data efficient and robust use of neural networks. While various approaches aiming towards…

Machine Learning · Statistics 2019-05-15 Raphael Suter , Đorđe Miladinović , Bernhard Schölkopf , Stefan Bauer

Biased attributes, spuriously correlated with target labels in a dataset, can problematically lead to neural networks that learn improper shortcuts for classifications and limit their capabilities for out-of-distribution (OOD)…

Computer Vision and Pattern Recognition · Computer Science 2024-03-22 Jinyung Hong , Eun Som Jeon , Changhoon Kim , Keun Hee Park , Utkarsh Nath , Yezhou Yang , Pavan Turaga , Theodore P. Pavlic

NLP research has attained high performances in abusive language detection as a supervised classification task. While in research settings, training and test datasets are usually obtained from similar data samples, in practice systems are…

Computation and Language · Computer Science 2021-05-21 Isar Nejadgholi , Svetlana Kiritchenko

Multimodal Large Language Models (MLLMs) have demonstrated strong performance in visual understanding tasks, yet they often suffer from object hallucinations--generating descriptions of objects that are inconsistent with or entirely absent…

Artificial Intelligence · Computer Science 2025-05-27 Xinmiao Hu , Chun Wang , Ruihe An , ChenYu Shao , Xiaojun Ye , Sheng Zhou , Liangcheng Li

Although achieving promising performance, recent analyses show that current generative large language models (LLMs) may still capture dataset biases and utilize them for generation, leading to poor generalizability and harmfulness of LLMs.…

Computation and Language · Computer Science 2024-09-02 Li Du , Zhouhao Sun , Xiao Ding , Yixuan Ma , Yang Zhao , Kaitao Qiu , Ting Liu , Bing Qin

Image classification models tend to make decisions based on peripheral attributes of data items that have strong correlation with a target variable (i.e., dataset bias). These biased models suffer from the poor generalization capability…

Machine Learning · Computer Science 2021-10-26 Jungsoo Lee , Eungyeup Kim , Juyoung Lee , Jihyeon Lee , Jaegul Choo

Large Language Models (LLMs) have shown their success in language understanding and reasoning on general topics. However, their capability to perform inference based on user-specified structured data and knowledge in corpus-rare concepts,…

Computation and Language · Computer Science 2024-10-29 Haitao Jiang , Lin Ge , Yuhe Gao , Jianian Wang , Rui Song
‹ Prev 1 2 3 10 Next ›