Toxicity in chatgpt: Analyzing persona-assigned language models.
Ameet Deshpande, Vishvak Murahari, Tanmay Rajpurohit, Ashwin Kalyan, Karthik Narasimhan
Browse the full EMNLP paper archive.
Ameet Deshpande, Vishvak Murahari, Tanmay Rajpurohit, Ashwin Kalyan, Karthik Narasimhan
Browse the full EMNLP paper archive.