4 papers
Explainable Ethical Assessment on Human Behaviors by Generating Conflicting Social Norms
Yuxi Sun, Wei Gao, Hongzhan Lin +2
Human behaviors are often guided or constrained by social norms, which are defined as shared, commonsense rules. For example, underlying an action ``\textit{report a witnessed crim…
CausalAbstain: Enhancing Multilingual LLMs with Causal Reasoning for Trustworthy Abstention
Yuxi Sun, Aoqi Zuo, Wei Gao +1
Large Language Models (LLMs) often exhibit knowledge disparities across languages. Encouraging LLMs to \textit{abstain} when faced with knowledge gaps is a promising strategy to re…
ClarityEthic: Explainable Moral Judgment Utilizing Contrastive Ethical Insights from Large Language Models
Yuxi Sun, Wei Gao, Jing Ma +3
With the rise and widespread use of Large Language Models (LLMs), ensuring their safety is crucial to prevent harm to humans and promote ethical behaviors. However, directly assess…
SHARP: Unlocking Interactive Hallucination via Stance Transfer in Role-Playing LLMs
Chuyi Kong, Ziyang Luo, Hongzhan Lin +4
The advanced role-playing capabilities of Large Language Models (LLMs) have enabled rich interactive scenarios, yet existing research in social interactions neglects hallucination…