English
Related papers

Related papers: Towards Debiasing NLU Models from Unknown Biases

200 papers

As Machine Learning models continue to be relied upon for making automated decisions, the issue of model bias becomes more and more prevalent. In this paper, we approach training a text classifica-tion model and optimize on bias…

Computation and Language · Computer Science 2019-08-19 Apik Ashod Zorian , Chandra Shekar Bikkanur

Datasets with significant proportions of bias present threats for training a trustworthy model on NLU tasks. Despite yielding great progress, current debiasing methods impose excessive reliance on the knowledge of bias attributes.…

Computation and Language · Computer Science 2022-09-19 Ting Wu , Tao Gui

As language models are increasingly included in human-facing machine learning tools, bias against demographic subgroups has gained attention. We propose FineDeb, a two-phase debiasing framework for language models that starts with…

Computation and Language · Computer Science 2023-02-07 Akash Saravanan , Dhruv Mullick , Habibur Rahman , Nidhi Hegde

Supervised machine learning models and their evaluation strongly depends on the quality of the underlying dataset. When we search for a relevant piece of information it may appear anywhere in a given passage. However, we observe a bias in…

Information Retrieval · Computer Science 2021-01-19 Sebastian Hofstätter , Aldo Lipani , Sophia Althammer , Markus Zlabinger , Allan Hanbury

An indigenous perspective on the effectiveness of debiasing techniques for pre-trained language models (PLMs) is presented in this paper. The current techniques used to measure and debias PLMs are skewed towards the US racial biases and…

Computation and Language · Computer Science 2023-04-24 Vithya Yogarajan , Gillian Dobbie , Henry Gouk

Improperly constructed datasets can result in inaccurate inferences. For instance, models trained on biased datasets perform poorly in terms of generalization (i.e., dataset bias). Recent debiasing techniques have successfully achieved…

Machine Learning · Computer Science 2022-12-05 Sumyeong Ahn , Se-Young Yun

Natural language processing models often exploit spurious correlations between task-independent features and labels in datasets to perform well only within the distributions they are trained on, while not generalising to different task…

Computation and Language · Computer Science 2022-03-25 Yuxiang Wu , Matt Gardner , Pontus Stenetorp , Pradeep Dasigi

Deep learning had already demonstrated its power in medical images, including denoising, classification, segmentation, etc. All these applications are proposed to automatically analyze medical images beforehand, which brings more…

Image and Video Processing · Electrical Eng. & Systems 2020-11-05 Shao-Cheng Wen , Yu-Jen Chen , Zihao Liu , Wujie Wen , Xiaowei Xu , Yiyu Shi , Tsung-Yi Ho , Qianjun Jia , Meiping Huang , Jian Zhuang

Neural networks predictions are unreliable when the input sample is out of the training distribution or corrupted by noise. Being able to detect such failures automatically is fundamental to integrate deep learning algorithms into robotics.…

Computer Vision and Pattern Recognition · Computer Science 2020-02-18 Antonio Loquercio , Mattia Segù , Davide Scaramuzza

Large Language Models (LLMs) have fundamentally transformed the field of natural language processing; however, their vulnerability to biases presents a notable obstacle that threatens both fairness and trust. This review offers an extensive…

Computation and Language · Computer Science 2025-09-19 Kiana Kiashemshaki , Mohammad Jalili Torkamani , Negin Mahmoudi , Meysam Shirdel Bilehsavar

Debiasing methods in NLP models traditionally focus on isolating information related to a sensitive attribute (e.g., gender or race). We instead argue that a favorable debiasing method should use sensitive information 'fairly,' with…

Computation and Language · Computer Science 2023-10-24 Bodhisattwa Prasad Majumder , Zexue He , Julian McAuley

The widespread use of machine learning and data-driven algorithms for decision making has been steadily increasing over many years. \emph{Bias} in the data can adversely affect this decision-making. We present a new mitigation strategy to…

Machine Learning · Computer Science 2025-07-25 Bruno Scarone , Alfredo Viola , Renée J. Miller , Ricardo Baeza-Yates

This thesis provides methods and analysis of models which make progress on this goal. The techniques outlined are task agnostic, and should provide benefit when used with nearly any transformer LM. We introduce two new finetuning methods…

Computation and Language · Computer Science 2024-08-30 Davis Yoshida

Large language models (LLMs) have achieved promising results in tabular data generation. However, inherent historical biases in tabular datasets often cause LLMs to exacerbate fairness issues, particularly when multiple advantaged and…

Machine Learning · Computer Science 2025-09-23 Tianchun Li , Tianci Liu , Xingchen Wang , Rongzhe Wei , Pan Li , Lu Su , Jing Gao

Feature selection is a prevalent data preprocessing paradigm for various learning tasks. Due to the expensive cost of acquiring supervision information, unsupervised feature selection sparks great interests recently. However, existing…

Machine Learning · Computer Science 2021-06-07 Xiaoying Xing , Hongfu Liu , Chen Chen , Jundong Li

Biases in existing datasets used to train algorithmic decision rules can raise ethical and economic concerns due to the resulting disparate treatment of different groups. We propose an algorithm for sequentially debiasing such datasets…

Machine Learning · Computer Science 2023-01-11 Yifan Yang , Yang Liu , Parinaz Naghizadeh

Pre-trained language models (PLMs) are trained on data that inherently contains gender biases, leading to undesirable impacts. Traditional debiasing methods often rely on external corpora, which may lack quality, diversity, or demographic…

Computation and Language · Computer Science 2025-03-13 Liu Yu , Ludie Guo , Ping Kuang , Fan Zhou

The rapid advancement of Vision-Language models (VLMs) has raised growing concerns that their black-box reasoning processes could lead to unintended forms of social bias. Current debiasing approaches focus on mitigating surface-level bias…

Computer Vision and Pattern Recognition · Computer Science 2026-03-02 Na Min An , Yoonna Jang , Yusuke Hirota , Ryo Hachiuma , Isabelle Augenstein , Hyunjung Shim

An increasing number of works in natural language processing have addressed the effect of bias on the predicted outcomes, introducing mitigation techniques that act on different parts of the standard NLP pipeline (data and models). However,…

Computation and Language · Computer Science 2020-09-15 Deven Shah , H. Andrew Schwartz , Dirk Hovy

Existing studies on bias mitigation methods for large language models (LLMs) use diverse baselines and metrics to evaluate debiasing performance, leading to inconsistent comparisons among them. Moreover, their evaluations are mostly based…

Computation and Language · Computer Science 2026-02-17 Xin Xu , Xunzhi He , Churan Zhi , Ruizhe Chen , Julian McAuley , Zexue He
‹ Prev 1 3 4 5 6 7 10 Next ›