相关论文: GECOBench: A Gender-Controlled Text Dataset and Be…

The task of image captioning implicitly involves gender identification. However, due to the gender bias in data, gender identification by an image captioning model suffers. Also, the gender-activity bias, owing to the word-by-word…

Language has a profound impact on our thoughts, perceptions, and conceptions of gender roles. Gender-inclusive language is, therefore, a key tool to promote social inclusion and contribute to achieving gender equality. Consequently,…

This paper proposes two intuitive metrics, skew and stereotype, that quantify and analyse the gender bias present in contextual language models when tackling the WinoBias pronoun resolution task. We find evidence that gender stereotype…

Image captioning has made substantial progress with huge supporting image collections sourced from the web. However, recent studies have pointed out that captioning datasets, such as COCO, contain gender bias found in web corpora. As a…

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…

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…

Large language models (LLMs) often inherit and amplify social biases embedded in their training data. A prominent social bias is gender bias. In this regard, prior work has mainly focused on gender stereotyping bias - the association of…

Recent works have found evidence of gender bias in models of machine translation and coreference resolution using mostly synthetic diagnostic datasets. While these quantify bias in a controlled experiment, they often do so on a small scale…

Text classification aims to effectively categorize documents into pre-defined categories. Traditional methods for text classification often rely on large amounts of manually annotated training data, making the process time-consuming and…

Large Language models (LLMs), such as ChatGPT, have gained popularity in recent years with the advancement of Natural Language Processing (NLP), with use cases spanning many disciplines and daily lives as well. LLMs inherit explicit and…

Gender bias in machine translation (MT) systems has been extensively documented, but bias in automatic quality estimation (QE) metrics remains comparatively underexplored. Existing studies suggest that QE metrics can also exhibit gender…

Societal biases present in pre-trained large language models are a critical issue as these models have been shown to propagate biases in countless downstream applications, rendering them unfair towards specific groups of people. Since…

The presence of social biases in large language models (LLMs) has become a significant concern in AI research. These biases, often embedded in training data, can perpetuate harmful stereotypes and distort decision-making processes. When…

Explainable AI (XAI) has emerged as a powerful tool for improving the performance of AI models, going beyond providing model transparency and interpretability. The scarcity of labeled data remains a fundamental challenge in developing…

Gender bias is highly impacting natural language processing applications. Word embeddings have clearly been proven both to keep and amplify gender biases that are present in current data sources. Recently, contextualized word embeddings…

Recent advances in Generative Artificial Intelligence (GenAI) have transformed educational content creation, particularly in developing tutor training materials. However, biases embedded in AI-generated content--such as gender, racial, or…

Convolutional Neural Networks (CNNs) are frequently and successfully used in medical prediction tasks. They are often used in combination with transfer learning, leading to improved performance when training data for the task are scarce.…

Predictive algorithms have a powerful potential to offer benefits in areas as varied as medicine or education. However, these algorithms and the data they use are built by humans, consequently, they can inherit the bias and prejudices…

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…

Explainable Artificial Intelligence (XAI) aims to provide transparent insights into machine learning models, yet the reliability of many feature attribution methods remains a critical challenge. Prior research (Haufe et al., 2014; Wilming…