Fine-tuning MiniCPM-o 4.5's language model with a LoRA on synthetic spoken calls transfers to unseen entities and an unseen business: on held-out cities and clinics, exact tool use rises from 25% to 67%, on an unseen car service centre from 25% to 79%, unconsented bookings or cancellations fall from 71 to 1 on the held-out test, and all 10 emergency calls are transferred at once.
Tables 1 and 2 directly report the exact percentages and counts cited in the claim, with bootstrap confidence intervals supporting the gains.
“It transfers. On held-out cities and clinics, the share of tool turns handled with the right tool and the right inputs rises from 25% to 67%, and on the unseen business from 25% to 79%. Bookings without consent fall from 71 to 1 on the held-out test, and all 10 emergency calls are transferred at once (§5).” · Show in paper