Prompt-Character Divergence: A Responsibility Compass for Human-AI Creative Collaboration

Maggie Wang, Wouter Haverals

Track: Paper

Keywords: Generative AI, Human–AI collaboration, Creative AI, Interpretability, Embedding-based metrics, Text-to-image models, Attribution drift

TL;DR: When AI makes "video-game plumber" look like Mario, who's responsible? We propose PC-D: a metric revealing whether outputs reflect user intent or model memory, helping creators navigate blurred authorship in AI-assisted creation.

Abstract: Distinguishing genuine user intent from model-driven echoes, whether of copyrighted characters, familiar styles, or training-derived identities, has become critical for creators as generative AI brings visual content creation to millions. Yet most detection tools remain computationally heavy, opaque, or inaccessible to the people they most affect. We present Prompt–Character Divergence (PC-D), a lightweight metric that quantifies semantic drift—how far a generated image aligns with known visual identities beyond what the prompt predicts. PC-D supports creator agency and responsibility in shared authorship by mapping outputs along two axes, name proximity and model drift, to produce a responsibility compass with four creative-agency zones: model-driven risk, mixed attribution, safe co-creation, and user-driven intent. Evaluated on three open-source models and ten iconic characters, PC-D captures drift patterns consistent with human judgment and runs on consumer hardware. Rather than resolving attribution, PC-D functions as a creator-facing diagnostic for self-auditing, helping practitioners determine when outputs reflect their intent, when they reflect the model’s learned biases, and how the two interact. The result is a practical, transparent aid that invites accessible, reflexive, and accountable human–AI collaboration.

Submission Number: 79