# Engineering of Hallucination in Generative AI: It's not a Bug, it's a Feature

arXiv: https://arxiv.org/abs/2601.07046 · HTML: https://mlsanity.com/paper/2601.07046/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 6 references that are in the map.
- First posted on arXiv 11 Jan 2026.

## Builds on (most cited first, 2 of 2)

- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [GAIA-1: A Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2309.17080/) (2023)

## Abstract (arXiv)

Generative artificial intelligence (AI) is conquering our lives at lightning speed. Large language models such as ChatGPT answer our questions or write texts for us, large computer vision models such as GAIA-1 generate videos on the basis of text descriptions or continue prompted videos. These neural network models are trained using large amounts of text or video data, strictly according to the real data employed in training. However, there is a surprising observation: When we use these models, they only function satisfactorily when they are allowed a certain degree of fantasy (hallucination). While hallucination usually has a negative connotation in generative AI - after all, ChatGPT is expected to give a fact-based answer! - this article recapitulates some simple means of probability engineering that can be used to encourage generative AI to hallucinate to a limited extent and thus lead to the desired results. We have to ask ourselves: Is hallucination in gen-erative AI probably not a bug, but rather a feature?