Evaluating the Effects of Prompt Perturbation on Bias and Hallucination in Large Language Models
It is shown that contrary to previous studies, perturbations can mitigate bias and hallucination in some LLMs over other models, and it's found that Claude 3 is more effective for the tasks represented in most datasets, whereas models like GPT3.5 exhibit varying levels of adequacy.
Mamehgol Yousefi, Ahmad Shahi, Mos Sharifi et al.
· International Conference on... · 0 citations