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 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to simplify Medicaid and CHIP applications through LLM APIs while addressing limitations such as hallucinations and outdated information by implementing a selective input process for clean and current data.
This study highlights a 2.2% increase in citizen satisfaction with federal services, reaching a seven-year high, driven by improvements in digital experiences, government processes, and complaint handling.
The Digital Benefit Network's Digital Identity Community of Practice held a session to hear considerations from civil rights technologists and human-centered design practitioners on ways to ensure program security while simultaneously promoting equity, enabling accessibility, and minimizing bias.
A case study documenting how a modular API layer was built to support a state-level paid family and medical leave program, improving interoperability, scalability, and user experience.
This report evaluates the effectiveness and implementation of a generative AI-powered assistive chatbot designed to help caseworkers navigate complex public benefit programs like Medicaid and SNAP.
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.
This research explores how software engineers are able to work with generative machine learning models. The results explore the benefits of generative code models and the challenges software engineers face when working with their outputs. The authors also argue for the need for intelligent user interfaces that help software engineers effectively work with generative code models.
