Generative AI for FFRDCs
This work addresses efficiency and security in government-related text analysis, but it is incremental as it applies existing methods (LLMs and OnPrem.LLM) to a specific domain.
The paper tackles the challenge of analyzing text-heavy workloads in Federally Funded Research and Development Centers (FFRDCs) by using large language models to accelerate tasks like summarization and classification with few examples, demonstrating enhanced oversight and strategic analysis in case studies on defense policy and scientific documents.
Federally funded research and development centers (FFRDCs) face text-heavy workloads, from policy documents to scientific and engineering papers, that are slow to analyze manually. We show how large language models can accelerate summarization, classification, extraction, and sense-making with only a few input-output examples. To enable use in sensitive government contexts, we apply OnPrem$.$LLM, an open-source framework for secure and flexible application of generative AI. Case studies on defense policy documents and scientific corpora, including the National Defense Authorization Act (NDAA) and National Science Foundation (NSF) Awards, demonstrate how this approach enhances oversight and strategic analysis while maintaining auditability and data sovereignty.