相关论文: Studying and Mitigating Biases in Sign Language Un…

Machine learning models fundamentally rely on large quantities of high-quality data. Collecting the necessary data for these models can be challenging due to cost, scarcity, and privacy restrictions. Signed languages are visual languages…

Many technologies for human-computer interaction have been designed for hearing individuals and depend upon vocalized speech, precluding users of American Sign Language (ASL) in the Deaf community from benefiting from these advancements.…

Although large language models (LLMs) have demonstrated their effectiveness in a wide range of applications, they have also been observed to perpetuate unwanted biases present in the training data, potentially leading to harm for…

Sign Language Recognition (SLR) is an essential yet challenging task since sign language is performed with the fast and complex movement of hand gestures, body posture, and even facial expressions. %Skeleton Aware Multi-modal Sign Language…

Progress in natural language generation research has been shaped by the ever-growing size of language models. While large language models pre-trained on web data can generate human-sounding text, they also reproduce social biases and…

Large language models (LLMs) acquire general linguistic knowledge from massive-scale pretraining. However, pretraining data mainly comprised of web-crawled texts contain undesirable social biases which can be perpetuated or even amplified…

Growing research in sign language recognition, generation, and translation AI has been accompanied by calls for ethical development of such technologies. While these works are crucial to helping individual researchers do better, there is a…

Despite their performance, large language models (LLMs) can inadvertently perpetuate biases found in the data they are trained on. By analyzing LLM responses to bias-eliciting headlines, we find that these models often mirror human biases.…

Recent advances in artificial intelligence, including the development of highly sophisticated large language models (LLM), have proven beneficial in many real-world applications. However, evidence of inherent bias encoded in these LLMs has…

Open-generation bias benchmarks evaluate social biases in Large Language Models (LLMs) by analyzing their outputs. However, the classifiers used in analysis often have inherent biases, leading to unfair conclusions. This study examines such…

Algorithms deployed in education can shape the learning experience and success of a student. It is therefore important to understand whether and how such algorithms might create inequalities or amplify existing biases. In this paper, we…

Speech AI Technologies are largely trained on publicly available datasets or by the massive web-crawling of speech. In both cases, data acquisition focuses on minimizing collection effort, without necessarily taking the data subjects'…

With the rapid progress of Large Language Models (LLMs), the general public now has easy and affordable access to applications capable of answering most health-related questions in a personalized manner. These LLMs are increasingly proving…

While Large Language Models (LLMs) have become ubiquitous in many fields, understanding and mitigating LLM biases is an ongoing issue. This paper provides a novel method for evaluating the demographic biases of various generative AI models.…

Large language models (LLMs) have demonstrated remarkable capabilities in simulating human behaviour and social intelligence. However, they risk perpetuating societal biases, especially when demographic information is involved. We introduce…

Models of sign language have historically lagged behind those for spoken language (text and speech). Recent work has greatly improved their performance on tasks like sign language translation and isolated sign recognition. However, it…

The rapid growth of Speech Emotion Recognition (SER) has diverse global applications, from improving human-computer interactions to aiding mental health diagnostics. However, SER models might contain social bias toward gender, leading to…

Many Natural Language Processing (NLP) systems use annotated corpora for training and evaluation. However, labeled data is often costly to obtain and scaling annotation projects is difficult, which is why annotation tasks are often…

Although many fairness criteria have been proposed to ensure that machine learning algorithms do not exhibit or amplify our existing social biases, these algorithms are trained on datasets that can themselves be statistically biased. In…

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…