相关论文: HERB: Measuring Hierarchical Regional Bias in Pre-…

Recent studies show that Natural Language Processing (NLP) technologies propagate societal biases about demographic groups associated with attributes such as gender, race, and nationality. To create interventions and mitigate these biases…

Machine learning techniques have been widely used in natural language processing (NLP). However, as revealed by many recent studies, machine learning models often inherit and amplify the societal biases in data. Various metrics have been…

When exposed to human-generated data, language models are known to learn and amplify societal biases. While previous works introduced benchmarks that can be used to assess the bias in these models, they rely on assumptions that may not be…

As NLP models become more integrated with the everyday lives of people, it becomes important to examine the social effect that the usage of these systems has. While these models understand language and have increased accuracy on difficult…

As Large Language Models (LLMs) become increasingly powerful and accessible to human users, ensuring fairness across diverse demographic groups, i.e., group fairness, is a critical ethical concern. However, current fairness and bias…

The presence of social biases in Natural Language Processing (NLP) and Information Retrieval (IR) systems is an ongoing challenge, which underlines the importance of developing robust approaches to identifying and evaluating such biases. In…

An increasing awareness of biased patterns in natural language processing resources, like BERT, has motivated many metrics to quantify `bias' and `fairness'. But comparing the results of different metrics and the works that evaluate with…

As Large Language Models (LLMs) are increasingly deployed to handle various natural language processing (NLP) tasks, concerns regarding the potential negative societal impacts of LLM-generated content have also arisen. To evaluate the…

Large Language Models (LLMs) inherit explicit and implicit biases from their training datasets. Identifying and mitigating biases in LLMs is crucial to ensure fair outputs, as they can perpetuate harmful stereotypes and misinformation. This…

Language models (LMs) are pretrained on diverse data sources, including news, discussion forums, books, and online encyclopedias. A significant portion of this data includes opinions and perspectives which, on one hand, celebrate democracy…

Pre-trained language models (PLMs) have revolutionized both the natural language processing research and applications. However, stereotypical biases (e.g., gender and racial discrimination) encoded in PLMs have raised negative ethical…

Rapid advancements of large language models (LLMs) have enabled the processing, understanding, and generation of human-like text, with increasing integration into systems that touch our social sphere. Despite this success, these models can…

Although large pre-trained language models have achieved great success in many NLP tasks, it has been shown that they reflect human biases from their pre-training corpora. This bias may lead to undesirable outcomes when these models are…

As Machine Learning technologies become increasingly used in contexts that affect citizens, companies as well as researchers need to be confident that their application of these methods will not have unexpected social implications, such as…

Double-blind peer review mechanism has become the skeleton of academic research across multiple disciplines including computer science, yet several studies have questioned the quality of peer reviews and raised concerns on potential biases…

This paper presents novel experiments shedding light on the shortcomings of current metrics for assessing biases of gender discrimination made by machine learning algorithms on textual data. We focus on the Bios dataset, and our learning…

Gender, race and social biases have recently been detected as evident examples of unfairness in applications of Natural Language Processing. A key path towards fairness is to understand, analyse and interpret our data and algorithms. Recent…

Recent literature has suggested the potential of using large language models (LLMs) to make classifications for tabular tasks. However, LLMs have been shown to exhibit harmful social biases that reflect the stereotypes and inequalities…

Unwanted and often harmful social biases are becoming ever more salient in NLP research, affecting both models and datasets. In this work, we ask whether training on demographically perturbed data leads to fairer language models. We collect…

As machine learning methods are deployed in real-world settings such as healthcare, legal systems, and social science, it is crucial to recognize how they shape social biases and stereotypes in these sensitive decision-making processes.…