Policy Violation
Policy violation research spans diverse domains, aiming to automatically detect and understand instances where rules, norms, or constraints are broken. Current efforts focus on developing machine learning models, including large language models and neural networks, to identify violations in various contexts, from social media content moderation and legal text analysis to environmental monitoring and medical adherence. These advancements offer significant potential for improving efficiency and accuracy in areas like online safety, regulatory compliance, and healthcare, while also raising important ethical considerations regarding bias and fairness in automated decision-making.
Papers
BAN-PL: a Novel Polish Dataset of Banned Harmful and Offensive Content from Wykop.pl web service
Anna Kołos, Inez Okulska, Kinga Głąbińska, Agnieszka Karlińska, Emilia Wiśnios, Paweł Ellerik, Andrzej Prałat
X-VoE: Measuring eXplanatory Violation of Expectation in Physical Events
Bo Dai, Linge Wang, Baoxiong Jia, Zeyu Zhang, Song-Chun Zhu, Chi Zhang, Yixin Zhu