Related papers: Debiasing Gender Bias in Information Retrieval Mod…
Artificial Intelligence has the capacity to amplify and perpetuate societal biases and presents profound ethical implications for society. Gender bias has been identified in the context of employment advertising and recruitment tools, due…
Gender bias in pretrained language models (PLMs) poses significant social and ethical challenges. Despite growing awareness, there is a lack of comprehensive investigation into how different models internally represent and propagate such…
With widening deployments of natural language processing (NLP) in daily life, inherited social biases from NLP models have become more severe and problematic. Previous studies have shown that word embeddings trained on human-generated…
Language model debiasing has emerged as an important field of study in the NLP community. Numerous debiasing techniques were proposed, but bias ablation remains an unaddressed issue. We demonstrate a novel framework for inspecting bias in…
Abusive language detection models tend to have a problem of being biased toward identity words of a certain group of people because of imbalanced training datasets. For example, "You are a good woman" was considered "sexist" when trained on…
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…
Pretrained machine learning models are known to perpetuate and even amplify existing biases in data, which can result in unfair outcomes that ultimately impact user experience. Therefore, it is crucial to understand the mechanisms behind…
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…
Contextual word embeddings such as BERT have achieved state of the art performance in numerous NLP tasks. Since they are optimized to capture the statistical properties of training data, they tend to pick up on and amplify social…
The blind application of machine learning runs the risk of amplifying biases present in data. Such a danger is facing us with word embedding, a popular framework to represent text data as vectors which has been used in many machine learning…
Multi-modal search engines have experienced significant growth and widespread use in recent years, making them the second most common internet use. While search engine systems offer a range of services, the image search field has recently…
Societal biases resonate in the retrieved contents of information retrieval (IR) systems, resulting in reinforcing existing stereotypes. Approaching this issue requires established measures of fairness in respect to the representation of…
Pre-trained large language models (LLMs) have been reliably integrated with visual input for multimodal tasks. The widespread adoption of instruction-tuned image-to-text vision-language assistants (VLAs) like LLaVA and InternVL necessitates…
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,…
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…
This study investigates the position bias in information retrieval, where models tend to overemphasize content at the beginning of passages while neglecting semantically relevant information that appears later. To analyze the extent and…
Mitigation of gender bias in NLP has a long history tied to debiasing static word embeddings. More recently, attention has shifted to debiasing pre-trained language models. We study to what extent the simplest projective debiasing methods,…
We investigate whether it is feasible to remove gendered information from resumes to mitigate potential bias in algorithmic resume screening. Using a corpus of 709k resumes from IT firms, we first train a series of models to classify the…
Machine translation (MT) technology has facilitated our daily tasks by providing accessible shortcuts for gathering, elaborating and communicating information. However, it can suffer from biases that harm users and society at large. As a…
Vast availability of text data has enabled widespread training and use of AI systems that not only learn and predict attributes from the text but also generate text automatically. However, these AI models also learn gender, racial and…