English
Related papers

Related papers: End-to-End Bias Mitigation by Modelling Biases in …

200 papers

Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual task labels, resulting in models learning "shortcuts". In…

Machine Learning · Computer Science 2024-08-12 Pietro Morerio , Ruggero Ragonesi , Vittorio Murino

Neural networks often learn to make predictions that overly rely on spurious correlation existing in the dataset, which causes the model to be biased. While previous work tackles this issue by using explicit labeling on the spuriously…

Machine Learning · Computer Science 2020-11-24 Junhyun Nam , Hyuntak Cha , Sungsoo Ahn , Jaeho Lee , Jinwoo Shin

Although large language models (LLMs) have demonstrated their effectiveness in a wide range of applications, they have also been observed to perpetuate unwanted biases present in the training data, potentially leading to harm for…

Computation and Language · Computer Science 2026-03-09 Schrasing Tong , Eliott Zemour , Jessica Lu , Rawisara Lohanimit , Lalana Kagal

Natural language understanding (NLU) models often rely on dataset biases rather than intended task-relevant features to achieve high performance on specific datasets. As a result, these models perform poorly on datasets outside the training…

Computation and Language · Computer Science 2023-01-05 Yougang Lyu , Piji Li , Yechang Yang , Maarten de Rijke , Pengjie Ren , Yukun Zhao , Dawei Yin , Zhaochun Ren

Large language models (LLMs) exhibit social biases that reinforce harmful stereotypes, limiting their safe deployment. Most existing debiasing methods adopt a suppressive paradigm by modifying parameters, prompts, or neurons associated with…

Artificial Intelligence · Computer Science 2026-01-30 Jinhao Pan , Chahat Raj , Anjishnu Mukherjee , Sina Mansouri , Bowen Wei , Shloka Yada , Ziwei Zhu

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

Popular Natural Language Inference (NLI) datasets have been shown to be tainted by hypothesis-only biases. Adversarial learning may help models ignore sensitive biases and spurious correlations in data. We evaluate whether adversarial…

Computation and Language · Computer Science 2019-07-11 Yonatan Belinkov , Adam Poliak , Stuart M. Shieber , Benjamin Van Durme , Alexander M. Rush

In this paper, we propose and experiment with techniques for extreme compression of neural natural language understanding (NLU) models, making them suitable for execution on resource-constrained devices. We propose a task-aware, end-to-end…

Computation and Language · Computer Science 2020-12-02 Kanthashree Mysore Sathyendra , Samridhi Choudhary , Leah Nicolich-Henkin

This paper reveals a data bias issue that can severely affect the performance while conducting a machine learning model for malicious URL detection. We describe how such bias can be identified using interpretable machine learning…

Machine Learning · Computer Science 2024-02-12 YunDa Tsai , Cayon Liow , Yin Sheng Siang , Shou-De Lin

Existing NLP datasets contain various biases, and models tend to quickly learn those biases, which in turn limits their robustness. Existing approaches to improve robustness against dataset biases mostly focus on changing the training…

Computation and Language · Computer Science 2020-10-26 Nafise Sadat Moosavi , Marcel de Boer , Prasetya Ajie Utama , Iryna Gurevych

Sensitivity of deep-neural models to input noise is known to be a challenging problem. In NLP, model performance often deteriorates with naturally occurring noise, such as spelling errors. To mitigate this issue, models may leverage…

Computation and Language · Computer Science 2021-11-18 Jakub Náplava , Martin Popel , Milan Straka , Jana Straková

Humans can learn languages from remarkably little experience. Developing computational models that explain this ability has been a major challenge in cognitive science. Bayesian models that build in strong inductive biases - factors that…

Computation and Language · Computer Science 2023-05-25 R. Thomas McCoy , Thomas L. Griffiths

The dominating NLP paradigm of training a strong neural predictor to perform one task on a specific dataset has led to state-of-the-art performance in a variety of applications (eg. sentiment classification, span-prediction based question…

Computation and Language · Computer Science 2021-09-06 Paul Michel

Neural network models have been very successful at achieving high accuracy on natural language inference (NLI) tasks. However, as demonstrated in recent literature, when tested on some simple adversarial examples, most of the models suffer…

Computation and Language · Computer Science 2019-09-04 Alexander Hanbo Li , Abhinav Sethy

Pretrained language models have been shown to exhibit biases and social stereotypes. Prior work on debiasing these models has largely focused on modifying embedding spaces during pretraining, which is not scalable for large models.…

Artificial Intelligence · Computer Science 2026-02-03 Deep Gandhi , Katyani Singh , Nidhi Hegde

While deep learning has resulted in major breakthroughs in many application domains, the frameworks commonly used in deep learning remain fragile to artificially-crafted and imperceptible changes in the data. In response to this fragility,…

Machine Learning · Computer Science 2020-11-03 Alexander Robey , Hamed Hassani , George J. Pappas

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

Entailment has been recognized as an important metric for evaluating natural language understanding (NLU) models, and recent studies have found that entailment pretraining benefits weakly supervised fine-tuning. In this work, we design a…

Computation and Language · Computer Science 2023-05-30 Jiaxin Ge , Hongyin Luo , Yoon Kim , James Glass

Recent generative large language models (LLMs) show remarkable performance in non-English languages, but when prompted in those languages they tend to express higher harmful social biases and toxicity levels. Prior work has shown that…

Computation and Language · Computer Science 2025-06-03 Vera Neplenbroek , Arianna Bisazza , Raquel Fernández

Deep neural networks often struggle to learn robust representations in the presence of dataset biases, leading to suboptimal generalization on unbiased datasets. This limitation arises because the models heavily depend on peripheral and…

Machine Learning · Computer Science 2024-12-11 Carlo Alberto Barbano , Enzo Tartaglione , Marco Grangetto