VeriForge: Mitigating Latent Knowledge Gaps in Narrative Drafting via Mixed-Initiative Scaffolding

2026-08-10

AI Summary

This work addresses the limitation of existing AI writing tools in transcending users’ cognitive boundaries, which often leads to homogeneous content generation. To overcome this, the paper proposes a hybrid proactive writing system that enables collaborative division of labor between authors and the AI through cognitive decoupling. The system constructs a graph-structured retrieval-augmented generation (RAG) pipeline from domain-specific materials to proactively surface relevant knowledge, presenting it via contextualized inline highlights and knowledge cards. Authors, in turn, concentrate on narrative composition. The system introduces a novel integration of proactive inline prompting, dual-stream querying, and a spatial knowledge canvas. User studies demonstrate that this approach effectively identifies knowledge gaps, stimulates creative exploration, and significantly enhances the domain authenticity of generated texts.

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.

Problem

• knowledge gaps
• narrative drafting
• domain knowledge
• AI writing tools
• verisimilitude

Innovation

• mixed-initiative scaffolding
• retrieval-augmented generation
• knowledge gap detection
• domain grounding
• Knowledge Canvas