Formally Verified Code Synthesis for Structured Data Translation in a Medical Internet of Things

Colin Samplawski, Adam D. Cobb

Keywords: LLMs, code synthesis, evolutionary algorithms, Medical Internet of Things, formal verification

TL;DR: We use LLMs to generate structured data translation which is formally verified to always match the output schema

Abstract: In this work we present a LLM powered, evolutionary code synthesis system for structured data translation in a Medical Internet of Things settings. A key challenge in this domain is ensuring that the synthesized code is trustworthy and reliable. To this end, we integrate a formal verification step into our code synthesis pipeline to ensure that any generated code is guaranteed to satisfy predefined requirements. In particular, we present a case study of integrating a novel device (a pulse oximeter) into the existing network of devices. Our system generates a formally verified translation between the device's JSON schema and the Fast Healthcare Interoperability Resources (FHIR) format used by the wider system. This formal verification stage ensures structured data translated by the generated code will always be in the target output schema. We provide a set of experimental results which demonstrate that our system is able to consistently generate correct translation at low cost.

Submission Number: 15