D2C-Routing: Dimension-to-Composition Evidence Routing for Mixed-Origin AI-Generated Text Detection
Year: 2026
Type: conference-paper
Abstract: AI-generated text detection is commonly framed as a binary document-level judgment about whether a text is human-written or machine-generated.This framing breaks down for mixed-origin writing, where content origin and expression origin may differ.We cast mixed-origin detection as dimension-to-composition source attribution, inferring content origin and expression origin before composing them into four collaboration types.We propose Dimension-to-Composition Routing (D2C-Routing), which routes content-side and expression-side evidence to supervised dimension heads before a learned gated composition layer predicts the final label.On MixD2C, a reconstructed split derived from the HART mixed-origin benchmark, our disclosed D2C-Routing-based detector system reaches 0.8603 four-way Avg TPR@1%FPR, 6.5 points above the samesplit RACE-local rerun.Core ablations support the routing design, while error analysis shows that distinguishing AI-content/humanexpression from fully AI-generated text remains the hardest boundary.Code is available at https://github.com/bystander563/d2c- routing-artifact.(A) Two independent attribution axes and resulting compositions HH Human content + Human expression Fully human-written text (B) Detection settings: what can be identified?Content-origin question Who produced the information plan and organization?Human Formulates ideas, selects evidence structures arguments AI Generates ideas, selects evidence, structures arguments
Institution: Beihang University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
Awards: G245388120, G6301420548
OpenAlex ID: W7204570335