Related papers: BOLD: Dataset and Metrics for Measuring Biases in …

We investigate bias trends in text-to-image generative models over time, focusing on the increasing availability of models through open platforms like Hugging Face. While these platforms democratize AI, they also facilitate the spread of…

Generative spoken language models produce speech in a wide range of voices, prosody, and recording conditions, seemingly approaching the diversity of natural speech. However, the extent to which generated speech is acoustically diverse…

Language models (LM) are becoming prevalent in many language-based application spaces globally. Although these LMs are improving our day-to-day interactions with digital products, concerns remain whether open-ended languages or text…

Text-to-Image (T2I) generative models are becoming increasingly crucial due to their ability to generate high-quality images, but also raise concerns about social biases, particularly in human image generation. Sociological research has…

Current datasets for unwanted social bias auditing are limited to studying protected demographic features such as race and gender. In this work, we introduce a comprehensive benchmark that is meant to capture the amplification of social…

We present a general approach towards controllable societal biases in natural language generation (NLG). Building upon the idea of adversarial triggers, we develop a method to induce societal biases in generated text when input prompts…

Humans quite frequently interact with conversational agents. The rapid advancement in generative language modeling through neural networks has helped advance the creation of intelligent conversational agents. Researchers typically evaluate…

Text representation models are prone to exhibit a range of societal biases, reflecting the non-controlled and biased nature of the underlying pretraining data, which consequently leads to severe ethical issues and even bias amplification.…

We generalize the notion of social biases from language embeddings to grounded vision and language embeddings. Biases are present in grounded embeddings, and indeed seem to be equally or more significant than for ungrounded embeddings. This…

Language models are trained on large-scale corpora that embed implicit biases documented in psychology. Valence associations (pleasantness/unpleasantness) of social groups determine the biased attitudes towards groups and concepts in social…

Large text corpora are increasingly important for a wide variety of Natural Language Processing (NLP) tasks, and automatic language identification (LangID) is a core technology needed to collect such datasets in a multilingual context.…

Warning: This paper contains explicit statements of offensive stereotypes which might be upsetting. Language models are prone to exhibiting biases, further amplifying unfair and harmful stereotypes. Given the fast-growing popularity and…

When evaluating the performance of automatic speech recognition models, usually word error rate within a certain dataset is used. Special care must be taken in understanding the dataset in order to report realistic performance numbers. We…

Pretrained Language Models (PLMs) harbor inherent social biases that can result in harmful real-world implications. Such social biases are measured through the probability values that PLMs output for different social groups and attributes…

Language models (LMs) have become pivotal in the realm of technological advancements. While their capabilities are vast and transformative, they often include societal biases encoded in the human-produced datasets used for their training.…

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.…

While biases in large language models (LLMs), such as stereotypes and cultural tendencies in outputs, have been examined and identified, their presence and characteristics in spoken dialogue models (SDMs) with audio input and output remain…

Human biases are ubiquitous but not uniform: disparities exist across linguistic, cultural, and societal borders. As large amounts of recent literature suggest, language models (LMs) trained on human data can reflect and often amplify the…

The surge in popularity of large language models has given rise to concerns about biases that these models could learn from humans. We investigate whether ingroup solidarity and outgroup hostility, fundamental social identity biases known…

Large-scale web-scraped text corpora used to train general-purpose AI models often contain harmful demographic-targeted social biases, creating a regulatory need for data auditing and developing scalable bias-detection methods. Although…