Related papers: Towards Identifying Social Bias in Dialog Systems:…
Dialogue safety problems severely limit the real-world deployment of neural conversational models and have attracted great research interests recently. However, dialogue safety problems remain under-defined and the corresponding dataset is…
Dialogue safety remains a pervasive challenge in open-domain human-machine interaction. Existing approaches propose distinctive dialogue safety taxonomies and datasets for detecting explicitly harmful responses. However, these taxonomies…
The use of dialogue systems as a medium for human-machine interaction is an increasingly prevalent paradigm. A growing number of dialogue systems use conversation strategies that are learned from large datasets. There are well documented…
Dialogue systems have been widely applied in many scenarios and are now more powerful and ubiquitous than ever before. With large neural models and massive available data, current dialogue systems have access to more knowledge than any…
Dialogue systems in the form of chatbots and personal assistants are being increasingly integrated into people's lives. Modern dialogue systems may consider adopting anthropomorphic personas, mimicking societal demographic groups to appear…
Social norms fundamentally shape interpersonal communication. We present NormDial, a high-quality dyadic dialogue dataset with turn-by-turn annotations of social norm adherences and violations for Chinese and American cultures. Introducing…
State-of-the-art conversational AI systems raise concerns due to their potential risks of generating unsafe, toxic, unethical, or dangerous content. Previous works have developed datasets to teach conversational agents the appropriate…
While large neural-based conversational models have become increasingly proficient dialogue agents, recent work has highlighted safety issues with these systems. For example, these systems can be goaded into generating toxic content, which…
Recently there are increasing concerns about the fairness of Artificial Intelligence (AI) in real-world applications such as computer vision and recommendations. For example, recognition algorithms in computer vision are unfair to black…
\textit{\textbf{\textcolor{red}{Warning}:} This paper contains content that may be offensive or upsetting.} Pretrained conversational agents have been exposed to safety issues, exhibiting a range of stereotypical human biases such as gender…
Recent advancements in Large Language Models empower them to follow freeform instructions, including imitating generic or specific demographic personas in conversations. We define generic personas to represent demographic groups, such as…
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.…
Machine learning approaches often require training and evaluation datasets with a clear separation between positive and negative examples. This risks simplifying and even obscuring the inherent subjectivity present in many tasks. Preserving…
During the past decade, several areas of speech and language understanding have witnessed substantial breakthroughs from the use of data-driven models. In the area of dialogue systems, the trend is less obvious, and most practical systems…
Powered by advanced Artificial Intelligence (AI) techniques, conversational AI systems, such as ChatGPT and digital assistants like Siri, have been widely deployed in daily life. However, such systems may still produce content containing…
Hate speech frequently appears on social media platforms and urgently needs to be effectively controlled. Alleviating the bias caused by hate speech can help resolve various ethical issues. Although existing research has constructed several…
Movies reflect society and also hold power to transform opinions. Social biases and stereotypes present in movies can cause extensive damage due to their reach. These biases are not always found to be the need of storyline but can creep in…
Speaker recognition is a widely used voice-based biometric technology with applications in various industries, including banking, education, recruitment, immigration, law enforcement, healthcare, and well-being. However, while dataset…
One challenge for dialogue agents is recognizing feelings in the conversation partner and replying accordingly, a key communicative skill. While it is straightforward for humans to recognize and acknowledge others' feelings in a…
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 ProsocialDialog, the first large-scale multi-turn dialogue…