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.
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.
This session from FormFest 2024 focused on how to help people get the assistance they need from the U.S. Department of Health and Human Services’ work on the Low Income Home Energy Assistance Program (LIHEAP) and the Maryland Social Services Administration’s work to improve welfare support for kinship caregivers.
This session from FormFest 2024 features the South Carolina Early Childhood Advisory Council’s work developing a single portal to integrate applications for publicly funded programs and services, and the office of Federal Student Aid’s work on the FAFSA form.
In this piece, the Digital Benefits Network shares several sources—from journalistic pieces, to reports and academic articles—we’ve found useful and interesting in our reading on automation and artificial intelligence.
This report highlights key findings from the Rules as Code Community of Practice, including practitioners' challenges with complex policies, their desire to share knowledge and resources, the need for increased training and support, and a collective interest in developing open standards and a shared code library.
When COVID-19 hit, the State of New Jersey recognized the need to both receive data on the spread of the disease from the public and provide information to them on how to mitigate it.
