# Choice Over Control: How Users Write with Large Language Models using Diegetic and Non-Diegetic Prompting

arXiv: https://arxiv.org/abs/2303.03199 · HTML: https://mlsanity.com/paper/2303.03199/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 55 references that are in the map.
- First posted on arXiv 6 Mar 2023.

## Builds on (most cited first, 21 of 21)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery](https://mlsanity.com/paper/2103.17249/) (2021)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [BARTScore: Evaluating Generated Text as Text Generation](https://mlsanity.com/paper/2106.11520/) (2021)
- [A Neural Representation of Sketch Drawings](https://mlsanity.com/paper/1704.03477/) (2017)
- [AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts](https://mlsanity.com/paper/2110.01691/) (2021)
- [CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities](https://mlsanity.com/paper/2201.06796/) (2022)
- [PromptChainer: Chaining Large Language Model Prompts through Visual Programming](https://mlsanity.com/paper/2203.06566/) (2022)
- [Gmail Smart Compose: Real-Time Assisted Writing](https://mlsanity.com/paper/1906.00080/) (2019)
- [BERTese: Learning to Speak to BERT](https://mlsanity.com/paper/2103.05327/) (2021)
- [Sparks: Inspiration for Science Writing using Language Models](https://mlsanity.com/paper/2110.07640/) (2021)
- [Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Models](https://mlsanity.com/paper/2208.07852/) (2022)
- [The Impact of Multiple Parallel Phrase Suggestions on Email Input and Composition Behaviour of Native and Non-Native English Writers](https://mlsanity.com/paper/2101.09157/) (2021)
- [Smart Reply: Automated Response Suggestion for Email](https://mlsanity.com/paper/1606.04870/) (2016)

## Built on by (most cited first, 30 of 36)

- [RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text](https://mlsanity.com/paper/2305.13304/) (2023)
- [A Design Space for Intelligent and Interactive Writing Assistants](https://mlsanity.com/paper/2403.14117/) (2024)
- [Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation](https://mlsanity.com/paper/2312.02439/) (2023)
- [The Homogenizing Effect of Large Language Models on Human Expression and Thought](https://mlsanity.com/paper/2508.01491/) (2025)
- [DataTales: Investigating the use of Large Language Models for Authoring Data-Driven Articles](https://mlsanity.com/paper/2308.04076/) (2023)
- [ABScribe: Rapid Exploration & Organization of Multiple Writing Variations in Human-AI Co-Writing Tasks using Large Language Models](https://mlsanity.com/paper/2310.00117/) (2023)
- [Understanding the LLM-ification of CHI: Unpacking the Impact of LLMs at CHI through a Systematic Literature Review](https://mlsanity.com/paper/2501.12557/) (2025)
- [Harnessing the Power of LLMs: Evaluating Human-AI Text Co-Creation through the Lens of News Headline Generation](https://mlsanity.com/paper/2310.10706/) (2023)
- ["It was 80% me, 20% AI": Seeking Authenticity in Co-Writing with Large Language Models](https://mlsanity.com/paper/2411.13032/) (2024)
- [Co-Writing with AI, on Human Terms: Aligning Research with User Demands Across the Writing Process](https://mlsanity.com/paper/2504.12488/) (2025)
- [Next Steps for Human-Centered Generative AI: A Technical Perspective](https://mlsanity.com/paper/2306.15774/) (2023)
- [Authors' Values and Attitudes Towards AI-bridged Scalable Personalization of Creative Language Arts](https://mlsanity.com/paper/2403.00439/) (2024)
- [Collage is the New Writing: Exploring the Fragmentation of Text and User Interfaces in AI Tools](https://mlsanity.com/paper/2405.17217/) (2024)
- [Innovative Thinking, Infinite Humor: Humor Research of Large Language Models through Structured Thought Leaps](https://mlsanity.com/paper/2410.10370/) (2024)
- [How Does the Disclosure of AI Assistance Affect the Perceptions of Writing?](https://mlsanity.com/paper/2410.04545/) (2024)
- [OmniActions: Predicting Digital Actions in Response to Real-World Multimodal Sensory Inputs with LLMs](https://mlsanity.com/paper/2405.03901/) (2024)
- [From Conversation to Orchestration: HCI Challenges and Opportunities in Interactive Multi-Agentic Systems](https://mlsanity.com/paper/2506.20091/) (2025)
- [CorpusStudio: Surfacing Emergent Patterns in a Corpus of Prior Work while Writing](https://mlsanity.com/paper/2503.12436/) (2025)
- [Collaborative Document Editing with Multiple Users and AI Agents](https://mlsanity.com/paper/2509.11826/) (2025)
- [A Systematic Review of Human-AI Co-Creativity](https://mlsanity.com/paper/2506.21333/) (2025)
- [Composable Prompting Workspaces for Creative Writing: Exploration and Iteration Using Dynamic Widgets](https://mlsanity.com/paper/2503.21394/) (2025)
- [CoCo Matrix: Taxonomy of Cognitive Contributions in Co-writing with Intelligent Agents](https://mlsanity.com/paper/2405.12438/) (2024)
- [Enabling Generative Design Tools with LLM Agents for Mechanical Computation Devices: A Case Study](https://mlsanity.com/paper/2405.17837/) (2024)
- [Content-Driven Local Response: Supporting Sentence-Level and Message-Level Mobile Email Replies With and Without AI](https://mlsanity.com/paper/2502.06430/) (2025)
- [PromptCanvas: Composable Prompting Workspaces Using Dynamic Widgets for Exploration and Iteration in Creative Writing](https://mlsanity.com/paper/2506.03741/) (2025)
- ["With Great Power Comes Great Responsibility!": Student and Instructor Perspectives on the influence of LLMs on Undergraduate Engineering Education](https://mlsanity.com/paper/2309.10694/) (2023)
- [Natural Language based Context Modeling and Reasoning for Ubiquitous Computing with Large Language Models: A Tutorial](https://mlsanity.com/paper/2309.15074/) (2023)
- [Exploring Mobile Touch Interaction with Large Language Models](https://mlsanity.com/paper/2502.07629/) (2025)
- [Comparing Native and Non-native English Speakers' Behaviors in Collaborative Writing through Visual Analytics](https://mlsanity.com/paper/2502.18681/) (2025)
- [PlayWrite: A Multimodal System for AI Supported Narrative Co-Authoring Through Play in XR](https://mlsanity.com/paper/2603.02366/) (2026)

## Abstract (arXiv)

We propose a conceptual perspective on prompts for Large Language Models (LLMs) that distinguishes between (1) diegetic prompts (part of the narrative, e.g. "Once upon a time, I saw a fox..."), and (2) non-diegetic prompts (external, e.g. "Write about the adventures of the fox."). With this lens, we study how 129 crowd workers on Prolific write short texts with different user interfaces (1 vs 3 suggestions, with/out non-diegetic prompts; implemented with GPT-3): When the interface offered multiple suggestions and provided an option for non-diegetic prompting, participants preferred choosing from multiple suggestions over controlling them via non-diegetic prompts. When participants provided non-diegetic prompts it was to ask for inspiration, topics or facts. Single suggestions in particular were guided both with diegetic and non-diegetic information. This work informs human-AI interaction with generative models by revealing that (1) writing non-diegetic prompts requires effort, (2) people combine diegetic and non-diegetic prompting, and (3) they use their draft (i.e. diegetic information) and suggestion timing to strategically guide LLMs.