Related papers: A Robust Bias Mitigation Procedure Based on the St…

Existing word embedding debiasing methods require social-group-specific word pairs (e.g., "man"-"woman") for each social attribute (e.g., gender), which cannot be used to mitigate bias for other social groups, making these methods…

Stereotypical language expresses widely-held beliefs about different social categories. Many stereotypes are overtly negative, while others may appear positive on the surface, but still lead to negative consequences. In this work, we…

Static word embeddings often absorb social biases from the text they learn from, and those biases can quietly shape downstream systems. Prior work that uses the Stereotype Content Model (SCM) has focused mostly on single-group bias along…

Word embeddings have been shown to produce remarkable results in tackling a vast majority of NLP related tasks. Unfortunately, word embeddings also capture the stereotypical biases that are prevalent in society, affecting the predictive…

As large vision language models(LVLMs) rapidly advance, concerns about their potential to learn and generate social biases and stereotypes are increasing. Previous studies on LVLM's stereotypes face two primary limitations: metrics that…

Large language models (LLMs) have shown remarkable advances in language generation and understanding but are also prone to exhibiting harmful social biases. While recognition of these behaviors has generated an abundance of bias mitigation…

Societal biases in the usage of words, including harmful stereotypes, are frequently learned by common word embedding methods. These biases manifest not only between a word and an explicit marker of its stereotype, but also between words…

Large Language Models (LLMs) have been observed to encode and perpetuate harmful associations present in the training data. We propose a theoretically grounded framework called StereoMap to gain insights into their perceptions of how…

The rapid increase in hate speech on social media has exposed an unprecedented impact on society, making automated methods for detecting such content important. Unlike prior black-box models, we propose a novel transparent method for…

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,…

Multi-modal Large Language Models (MLLMs) have dramatically advanced the research field and delivered powerful vision-language understanding capabilities. However, these models often inherit deep-rooted social biases from their training…

Fine-tuned language models have been shown to exhibit biases against protected groups in a host of modeling tasks such as text classification and coreference resolution. Previous works focus on detecting these biases, reducing bias in data…

Concept Bottleneck Models (CBMs) enhance interpretability by predicting human-understandable concepts as intermediate representations. However, existing CBMs often suffer from input-to-concept mapping bias and limited controllability, which…

Machine learning algorithms are optimized to model statistical properties of the training data. If the input data reflects stereotypes and biases of the broader society, then the output of the learning algorithm also captures these…

Speech foundation models (SFMs), such as Open Whisper-Style Speech Models (OWSM), are trained on massive datasets to achieve accurate automatic speech recognition. However, even SFMs struggle to accurately recognize rare and unseen words.…

Ensuring fairness in image classification prevents models from perpetuating and amplifying bias. Concept bottleneck models (CBMs) map images to high-level, human-interpretable concepts before making predictions via a sparse, one-layer…

Recent advancements in text-to-image models, such as Stable Diffusion, show significant demographic biases. Existing de-biasing techniques rely heavily on additional training, which imposes high computational costs and risks of compromising…

It is well known that textual data on the internet and other digital platforms contain significant levels of bias and stereotypes. Although many such texts contain stereotypes and biases that inherently exist in natural language for reasons…

Due to their similarity-based learning objectives, pretrained sentence encoders often internalize stereotypical assumptions that reflect the social biases that exist within their training corpora. In this paper, we describe several kinds of…

Word embeddings learnt from massive text collections have demonstrated significant levels of discriminative biases such as gender, racial or ethnic biases, which in turn bias the down-stream NLP applications that use those word embeddings.…