A recap of the two-day conference focused on charting the course to excellence in digital benefits delivery hosted at Georgetown University and online.
The Policy2Code Prototyping Challenge explored utilizing generative AI technology to translate U.S. government policies for public benefits into plain language and code, culminating in a Demo Day where twelve teams showcased their projects for feedback and evaluation.
The team introduced an AI assistant for benefits navigators to streamline the process and improve outcomes by quickly assessing client eligibility for benefits programs.
The team introduced "Policy Pulse," a tool to help policy analysts understand laws and regulations better by comparing current policies with their original goals to identify implementation issues.
The team aimed to automate applying rules efficiently by creating computable policies, recognizing the need for AI tools to convert legacy policy content into automated business rules using Decision Model Notation (DMN) for effective processing and monitoring.
The team explored the performance of various AI chatbots and LLMs in supporting the adoption of Rules as Code for SNAP and Medicaid policies using policy data from Georgia and Oklahoma.
The team developed an application to simplify Medicaid and CHIP applications through LLM APIs while addressing limitations such as hallucinations and outdated information by implementing a selective input process for clean and current data.
The team developed an application to simplify Medicaid and CHIP applications through LLM APIs while addressing limitations such as hallucinations and outdated information by implementing a selective input process for clean and current data.
The team explored using LLMs to interpret the Program Operations Manual System (POMS) into plain language logic models and flowcharts as educational resources for SSI and SSDI eligibility, benchmarking LLMs in RAG methods for reliability in answering queries and providing useful instructions to users.
The team examined how AI, specifically LLMs, could streamline the case review process for SNAP applications to alleviate the burden on case workers while potentially improving accuracy.
The team developed an AI-powered explanation feature that effectively translates complex, multi-program policy calculations into clear and accessible explanations, enabling users to explore "what-if" scenarios and understand key factors influencing benefit amounts and eligibility thresholds.
The team developed an AI solution to assist benefit navigators with in-the-moment program information, finding that while LLMs are useful for summarizing and interpreting text, they are not ideal for implementing strict formulas like benefit calculations, but can accelerate the eligibility process by leveraging their strengths in general tasks.
