Writer-Defined AI Personas for On-Demand Feedback Generation
arXiv:2309.10433 · doi:10.1145/3613904.3642406
Abstract
Compelling writing is tailored to its audience. This is challenging, as writers may struggle to empathize with readers, get feedback in time, or gain access to the target group. We propose a concept that generates on-demand feedback, based on writer-defined AI personas of any target audience. We explore this concept with a prototype (using GPT-3.5) in two user studies (N=5 and N=11): Writers appreciated the concept and strategically used personas for getting different perspectives. The feedback was seen as helpful and inspired revisions of text and personas, although it was often verbose and unspecific. We discuss the impact of on-demand feedback, the limited representativity of contemporary AI systems, and further ideas for defining AI personas. This work contributes to the vision of supporting writers with AI by expanding the socio-technical perspective in AI tool design: To empower creators, we also need to keep in mind their relationship to an audience.
18 pages, 8 figures, 3 tables
References in corpus (11)
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Expanding Explainability: Towards Social Transparency in AI systems
- CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities
- Co-Writing with Opinionated Language Models Affects Users' Views
- A Design Space for Intelligent and Interactive Writing Assistants
- Beyond Text Generation: Supporting Writers with Continuous Automatic Text Summaries
- Interacting with next-phrase suggestions: How suggestion systems aid and influence the cognitive processes of writing
- CharacterChat: Supporting the Creation of Fictional Characters through Conversation and Progressive Manifestation with a Chatbot
- Exploiting Persona Information for Diverse Generation of Conversational Responses
- BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data
- Writing Assistants Should Model Social Factors of Language
Cited by in corpus (22)
- From Pen to Prompt: How Creative Writers Integrate AI into their Writing Practice
- Co-Writing with AI, on Human Terms: Aligning Research with User Demands Across the Writing Process
- PersonaFlow: Designing LLM-Simulated Expert Perspectives for Enhanced Research Ideation
- Collage is the New Writing: Exploring the Fragmentation of Text and User Interfaces in AI Tools
- AI Rivalry as a Craft: How Resisting and Embracing Generative AI Reshape Writing Professions
- Creative Writers' Attitudes on Writing as Training Data for Large Language Models
- tAIfa: Enhancing Team Effectiveness and Cohesion with AI-Generated Automated Feedback
- Not Like Us, Hunty: Measuring Perceptions and Behavioral Effects of Minoritized Anthropomorphic Cues in LLMs
- Composable Prompting Workspaces for Creative Writing: Exploration and Iteration Using Dynamic Widgets
- StoryEnsemble: Enabling Dynamic Exploration & Iteration in the Design Process with AI and Forward-Backward Propagation
- Exploring Mobile Touch Interaction with Large Language Models
- Surfacing Variations to Calibrate Perceived Reliability of MLLM-generated Image Descriptions
- CorpusStudio: Surfacing Emergent Patterns in a Corpus of Prior Work while Writing
- RevTogether: Supporting Science Story Revision with Multiple AI Agents
- Teaming in the AI Era: AI-Augmented Frameworks for Forming, Simulating, and Optimizing Human Teams
- Creating and Evaluating Personas Using Generative AI: A Scoping Review of 81 Articles
- Accessibility Scout: Personalized Accessibility Scans of Built Environments
- Wisdom of the Crowd, Without the Crowd: A Socratic LLM for Asynchronous Deliberation on Perspectivist Data
- Using AI for User Representation: An Analysis of 83 Persona Prompts
- TalkLess: Blending Extractive and Abstractive Speech Summarization for Editing Speech to Preserve Content and Style
- Constella: Supporting Storywriters' Interconnected Character Creation through LLM-based Multi-Agents
- StudyAlign: A Software System for Conducting Web-Based User Studies with Functional Interactive Prototypes