Definition
Hallucination is when a language model confidently produces content that is factually false or fabricated — nonexistent citations, invented APIs, made-up history. It’s the most user-visible failure mode of LLMs and a major frontier problem for any deployment where being wrong is expensive.
Episodes covering this
Worth reading next
Papers we haven't done a deep dive on yet, but would recommend on this topic.
- Language Models (Mostly) Know What They Know
- Calibration of Large Language Models Using Their Generations
- Faithful Chain-of-Thought Reasoning
- Training language models to follow instructions with human feedback
- Calibration of Large Language Models Using Their Generations
- Chain of Thought Empowers Transparent Reasoning of Language Models
- Calibration of Large Language Models Using Their Generations
- SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models
- Chain-of-Verification Reduces Hallucination in Large Language Models