2 code implementations • 7 Apr 2024 • Pouya Fallah, Soroush Gooran, Mohammad Jafarinasab, Pouya Sadeghi, Reza Farnia, Amirreza Tarabkhah, Zainab Sadat Taghavi, Hossein Sameti
Language models, particularly generative models, are susceptible to hallucinations, generating outputs that contradict factual knowledge or the source text.