Interpretable Directed Diversity: Leveraging Model Explanations for Iterative Crowd Ideation

Abstract

Feedback in creativity support tools can help crowdworkers to improve their ideations. However, current feedback methods require human assessment from facilitators or peers. This is not scalable to large crowds. We propose Interpretable Directed Diversity to automatically predict ideation quality and diversity scores, and provide AI explanations - Attribution, Contrastive Attribution, and Counterfactual Suggestions - to feedback on why ideations were scored (low), and how to get higher scores. These explanations provide multi-faceted feedback as users iteratively improve their ideations. We conducted formative and controlled user studies to understand the usage and usefulness of explanations to improve ideation diversity and quality. Users appreciated that explanation feedback helped focus their efforts and provided directions for improvement. This resulted in explanations improving diversity compared to no feedback or feedback with scores only. Hence, our approach opens opportunities for explainable AI towards scalable and rich feedback for iterative crowd ideation and creativity support tools.

References in corpus (6)

• Building a Conversational Agent Overnight with Dialogue Self-Play
• Towards Relatable Explainable AI with the Perceptual Process
• Leveraging Rationales to Improve Human Task Performance
• Spinneret: Aiding Creative Ideation through Non-Obvious Concept Associations
• Hardhats and Bungaloos: Comparing Crowdsourced Design Feedback with Peer Design Feedback in the Classroom
• Supporting Creative Work with Crowd Feedback Systems

Cited by in corpus (7)

• Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations
• RePrompt: Automatic Prompt Editing to Refine AI-Generative Art Towards Precise Expressions
• ScatterShot: Interactive In-context Example Curation for Text Transformation
• Co-Writing with AI, on Human Terms: Aligning Research with User Demands Across the Writing Process
• Redefining Research Crowdsourcing: Incorporating Human Feedback with LLM-Powered Digital Twins
• GenTune: Toward Traceable Prompts to Improve Controllability of Image Refinement in Environment Design
• Varif.ai to Vary and Verify User-Driven Diversity in Scalable Image Generation