epochs

Learn · Module 06 · Transformers · Lesson 5 of 6

Why models hallucinate

A language model always produces an answer, even when it doesn't know one. Understanding why is the first step to designing around it.

4 minute read

In short
  • Models produce the most likely text, not the true text, so they guess fluently when they don't know.
  • Rare facts, outdated knowledge and leading questions make hallucination more likely.
  • Ground answers in sources, allow 'I don't know', and verify high-stakes claims.

This lesson is part of Pro

The first two lessons of every module are free. Pro opens every lesson and every project.

See Pro plansFrom ₹119 a month. No auto-renewal.