Why Language Models Hallucinate

Hallucinations are the predictable result of training and grading that reward confident guessing.

Kalai et al. · arXiv 2025 · Reasoning & RL. Read the paper ↗

A free, interactive, animated visual explainer of Why Language Models Hallucinate — every exhibit computed from the real formulas, with verbatim quotes from the source.

Questions

What is Why Language Models Hallucinate?
Hallucinations are the predictable result of training and grading that reward confident guessing.
Who published Why Language Models Hallucinate, and where?
Kalai et al. — arXiv 2025 (arXiv:2509.04664).
Where can I find a visual explainer of Why Language Models Hallucinate?
Right here — a free, interactive, animated walkthrough of the whole paper, with exhibits computed from the real formulas and verbatim quotes from the source.

Related explainers