Theory of mind (ToM) refers to humans' ability to understand and infer t...
Objective: To assess the performance of the OpenAI GPT API in accurately...
With the rapid popularity of large language models such as ChatGPT and G...
With the development of artificial intelligence, dialogue systems have b...
Large pretrained language models can easily produce toxic or biased cont...
Recently, amounts of works utilize perplexity (PPL) to evaluate the qual...
Offensive language detection and prevention becomes increasing critical ...
Dialogue safety problems severely limit the real-world deployment of neu...