Large language models (LLMs) have shown powerful performance and development
prospect and are widely deployed in the real world. However, LLMs can capture social …

Detecting online toxicity has always been a challenge due to its inherent subjectivity. Factors
such as the context, geography, socio-political climate, and background of the producers …

Toxic language detection systems often falsely flag text that contains minority group
mentions as toxic, as those groups are often the targets of online hate. Such over-reliance …

AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …

Majority voting and averaging are common approaches used to resolve annotator
disagreements and derive single ground truth labels from multiple annotations. However …

Large language models (LM) generate remarkably fluent text and can be efficiently adapted
across NLP tasks. Measuring and guaranteeing the quality of generated text in terms of …

Most existing dialogue systems fail to respond properly to potentially unsafe user utterances
by either ignoring or passively agreeing with them. To address this issue, we introduce …

Internet memes have become powerful means to transmit political, psychological, and socio-
cultural ideas. Although memes are typically humorous, recent days have witnessed an …

As the reach of large language models (LMs) expands globally, their ability to cater to
diverse cultural contexts becomes crucial. Despite advancements in multilingual …

The social impact of natural language processing and its applications has received
increasing attention. In this position paper, we focus on the problem of safety for end-to-end …