Language Twin: A Shared-State Architecture for Terminology-Consistent Document Translation with Human Edit Propagation—A Pilot Study

We propose Language Twin, a shared-state architecture that organizes translation projects as seven versioned layers (L0–L6), supporting selective context loading, scoped human-edit propagation, and reversible updates. A pilot study translated three curated English-to-Korean document bundles (17 segments) using GPT-4o with temperature 0.3. The Language Twin condition (P1) achieved numerically higher preferred-term accuracy than the strongest baseline (17/21 vs. 14/21; not statistically significant at this sample size) and observed no repeated downstream errors in the monitored set (0/5 vs. 5/5 against the propagation-disabled ablation; Fisher’s exact p = 0.008), while reducing prompt tokens by 39.2% relative to full-context loading (A4). In blinded human evaluation (quadratic-weighted κ = 0.71–0.78), P1 achieved the highest terminology rating (4.38/5 vs. 3.97/5) and lowest post-editing time (16.9 s vs. 19.1 s per segment). These pilot-scale results indicate that governed shared state can improve terminology consistency and editing efficiency.