Hallucination vs Confabulation: Why LLMs Invent Answers Instead of Saying “I Don’t Know”
中文摘要
本文探讨了LLM产生幻觉与虚构的原因，解释了模型为何倾向于编造看似合理的答案而非承认不知道。
English Summary
This article explains why LLMs invent plausible but false answers (hallucinations/confabulations) instead of admitting they lack information.
原文节选
When a model has no real fact to give you, it usually doesn’t stay silent. It fills the gap with the most plausible continuation, and it… Continue reading on Medium »