SOURCE-LINKED INTELLIGENCE

Towards a Deterministic Math Solver for Clinical Language Models

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

Large language models are unreliable at arithmetic, which is a problem for clinical calculators where a single numerical error changes the recommendation. The standard response is to hardcode each calculator as a validated function, one at a time. We test an alternative: the model does not calculate. Instead, it writes case-specific Python that a restricted local executor runs as a deterministic solver, and the model's task reduces to deciding how to use it. We evaluate this Program-Solve interface on MedCalc-Bench Verified (1,100 cases, 55 calculators) against direct model arithmetic and a ha

Read original source ↗ Open in workspace

recordType

paper

region

Global