English
Related papers

Related papers: Mind the Trade-off: Debiasing NLU Models without D…

200 papers

Learning general representations of text is a fundamental problem for many natural language understanding (NLU) tasks. Previously, researchers have proposed to use language model pre-training and multi-task learning to learn robust…

Computation and Language · Computer Science 2019-08-29 Zi-Yi Dou , Keyi Yu , Antonios Anastasopoulos

It is often observed in knowledge-centric tasks (e.g., common sense question and answering, relation classification) that the integration of external knowledge such as entity representation into language models can help provide useful…

Computation and Language · Computer Science 2021-09-03 Ruochen Xu , Yuwei Fang , Chenguang Zhu , Michael Zeng

Natural language understanding (NLU) models tend to rely on spurious correlations (i.e., dataset bias) to achieve high performance on in-distribution datasets but poor performance on out-of-distribution ones. Most of the existing debiasing…

Computation and Language · Computer Science 2022-09-14 Shihan Dou , Rui Zheng , Ting Wu , SongYang Gao , Junjie Shan , Qi Zhang , Yueming Wu , Xuanjing Huang

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

Many studies have shown various biases targeting different demographic groups in language models, amplifying discrimination and harming fairness. Recent parameter modification debiasing approaches significantly degrade core capabilities…

Computation and Language · Computer Science 2025-10-01 Dianqing Liu , Yi Liu , Guoqing Jin , Zhendong Mao

When working with textual data, a natural application of disentangled representations is fair classification where the goal is to make predictions without being biased (or influenced) by sensitive attributes that may be present in the data…

Computation and Language · Computer Science 2022-10-10 Pierre Colombo , Guillaume Staerman , Nathan Noiry , Pablo Piantanida

Free-text explanations are expressive and easy to understand, but many datasets lack annotated explanation data, making it challenging to train models for explainable predictions. To address this, we investigate how to use existing…

Computation and Language · Computer Science 2025-02-10 Jing Yang , Max Glockner , Anderson Rocha , Iryna Gurevych

To mitigate societal biases implicitly encoded in recent successful pretrained language models, a diverse array of approaches have been proposed to encourage model fairness, focusing on prompting, data augmentation, regularized fine-tuning,…

Computation and Language · Computer Science 2025-01-30 Jingxuan Xu , Wuyang Chen , Linyi Li , Yao Zhao , Yunchao Wei

Trained classification models can unintentionally lead to biased representations and predictions, which can reinforce societal preconceptions and stereotypes. Existing debiasing methods for classification models, such as adversarial…

Computation and Language · Computer Science 2021-09-23 Aili Shen , Xudong Han , Trevor Cohn , Timothy Baldwin , Lea Frermann

Curriculum Learning (CL) is a technique of training models via ranking examples in a typically increasing difficulty trend with the aim of accelerating convergence and improving generalisability. Current approaches for Natural Language…

Computation and Language · Computer Science 2022-11-28 Fenia Christopoulou , Gerasimos Lampouras , Ignacio Iacobacci

Gender bias exists in natural language datasets which neural language models tend to learn, resulting in biased text generation. In this research, we propose a debiasing approach based on the loss function modification. We introduce a new…

Computation and Language · Computer Science 2019-06-05 Yusu Qian , Urwa Muaz , Ben Zhang , Jae Won Hyun

In order to build reliable and trustworthy NLP applications, models need to be both fair across different demographics and explainable. Usually these two objectives, fairness and explainability, are optimized and/or examined independently…

Computation and Language · Computer Science 2023-11-14 Stephanie Brandl , Emanuele Bugliarello , Ilias Chalkidis

Web-scale pre-training datasets are the cornerstone of LLMs' success. However, text data curated from the Internet inevitably contains random noise caused by decoding errors or unregulated web content. In contrast to previous works that…

Computation and Language · Computer Science 2025-05-19 Jinghan Ru , Yuxin Xie , Xianwei Zhuang , Yuguo Yin , Zhihui Guo , Zhiming Liu , Qianli Ren , Yuexian Zou

With the introduction of (large) language models, there has been significant concern about the unintended bias such models may inherit from their training data. A number of studies have shown that such models propagate gender stereotypes,…

Computation and Language · Computer Science 2024-08-20 Rameez Qureshi , Naïm Es-Sebbani , Luis Galárraga , Yvette Graham , Miguel Couceiro , Zied Bouraoui

People frequently interact with information retrieval (IR) systems, however, IR models exhibit biases and discrimination towards various demographics. The in-processing fair ranking methods provide a trade-offs between accuracy and fairness…

Information Retrieval · Computer Science 2022-05-20 Yuantong Li , Xiaokai Wei , Zijian Wang , Shen Wang , Parminder Bhatia , Xiaofei Ma , Andrew Arnold

Discriminative pre-trained language models (PrLMs) can be generalized as denoising auto-encoders that work with two procedures, ennoising and denoising. First, an ennoising process corrupts texts with arbitrary noising functions to…

Computation and Language · Computer Science 2022-10-12 Zhuosheng Zhang , Hai Zhao , Ming Zhou

In a spoken dialogue system, an NLU model is preceded by a speech recognition system that can deteriorate the performance of natural language understanding. This paper proposes a method for investigating the impact of speech recognition…

Computation and Language · Computer Science 2023-10-26 Marek Kubis , Paweł Skórzewski , Marcin Sowański , Tomasz Ziętkiewicz

Current debiasing approaches often result a degradation in model capabilities such as factual accuracy and knowledge retention. Through systematic evaluation across multiple benchmarks, we demonstrate that existing debiasing methods face…

Machine Learning · Computer Science 2025-05-27 Buse Sibel Korkmaz , Rahul Nair , Elizabeth M. Daly , Antonio del Rio Chanona

While Vision-Language Models (VLMs) have achieved remarkable performance across diverse downstream tasks, recent studies have shown that they can inherit social biases from the training data and further propagate them into downstream…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Tangzheng Lian , Guanyu Hu , Yijing Ren , Dimitrios Kollias , Oya Celiktutan

We present an empirical study of debiasing methods for classifiers, showing that debiasers often fail in practice to generalize out-of-sample, and can in fact make fairness worse rather than better. A rigorous evaluation of the debiasing…