VeriForge: Mitigating Latent Knowledge Gaps in Narrative Drafting via Mixed-Initiative Scaffolding
2026-08-10 • Human-Computer Interaction
Human-Computer InteractionComputation and Language
AI summaryⓘ
The authors created VeriForge, a writing tool that helps fiction writers find and fill gaps in their knowledge about specific topics while writing stories. Unlike other AI tools, VeriForge highlights where writers might need more facts and offers helpful information without taking over the creative process. It uses a mix of highlights, question-answering, and an organized visual space to make learning and using new details easier. Their study with writers showed that VeriForge helps authors notice missing details, explore ideas better, and write more believable stories.
verisimilitudedomain knowledgemixed-initiative systemretrieval-augmented generationknowledge gapsinline highlightingKnowledge CardsKnowledge Canvas
Authors
Ruqi Sun, Jiaping Li, Wenhui Tao, Ximing Zheng, Yuefeng Tan, Jiahao Wei, Yuxin Ma
Abstract
Great fiction earns its verisimilitude through precise details, from how a longsword is gripped to pierce armor gaps to why a bleeding corpse cannot yet smell of decay, weaving domain expertise into the fabric of invented worlds. Current AI writing tools offer limited support for discovering and integrating unfamiliar domain knowledge into narrative. They require explicit queries that authors cannot formulate, generate finished prose that risks homogenizing voice, or assist only within the boundaries of what authors already know. We argue that AI should reveal latent knowledge gaps to writers while preserving their agency to transform discovered knowledge into authentic prose. Grounded in formative interviews with 9 fiction writers, we present VeriForge, a mixed-initiative writing system that divides cognitive labor so that the system assumes initiative over domain discovery while the author retains full initiative over narrative synthesis. VeriForge realizes this through three complementary mechanisms. Proactive inline highlighting flags potential knowledge gaps as authors draft. Dual-stream querying pairs conversational responses with source-anchored Knowledge Cards for direct fact extraction. A spatial Knowledge Canvas allows authors to organize and connect discovered knowledge across their writing. These mechanisms are powered by a graph-based retrieval-augmented generation pipeline grounded in domain-specific source materials. A within-subjects user study (N=12) provides preliminary evidence that this paradigm helps authors recognize previously overlooked knowledge gaps, supports creative exploration, and is perceived by expert raters to produce passages with stronger domain grounding in a controlled cold-start writing task.