# Multiversal views on language models

arXiv: https://arxiv.org/abs/2102.06391 · HTML: https://mlsanity.com/paper/2102.06391/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 11 references that are in the map.
- First posted on arXiv 12 Feb 2021.

## Builds on (most cited first, 1 of 1)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)

## Built on by (most cited first, 6 of 6)

- [Role-Play with Large Language Models](https://mlsanity.com/paper/2305.16367/) (2023)
- [On the Creativity of Large Language Models](https://mlsanity.com/paper/2304.00008/) (2023)
- [Simulacra as Conscious Exotica](https://mlsanity.com/paper/2402.12422/) (2024)
- [Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition](https://mlsanity.com/paper/2410.05603/) (2024)
- [Palatable Conceptions of Disembodied Being](https://mlsanity.com/paper/2503.16348/) (2025)
- [The Xeno Sutra: Can Meaning and Value be Ascribed to an AI-Generated "Sacred" Text?](https://mlsanity.com/paper/2507.20525/) (2025)

## Abstract (arXiv)

The virtuosity of language models like GPT-3 opens a new world of possibility for human-AI collaboration in writing. In this paper, we present a framework in which generative language models are conceptualized as multiverse generators. This framework also applies to human imagination and is core to how we read and write fiction. We call for exploration into this commonality through new forms of interfaces which allow humans to couple their imagination to AI to write, explore, and understand non-linear fiction. We discuss the early insights we have gained from actively pursuing this approach by developing and testing a novel multiversal GPT-3-assisted writing interface.