Leveraging LLMs to Streamline the Review of Public Funding Applications

2025-10-08

AI Summary

A surge in EU public funding applications has created severe bottlenecks in manual review processes. To address this, we propose the first large language model (LLM)-based review assistance framework designed for real-world governmental administration, integrating a rule-based engine with a confidence-aware filtering mechanism to enable high-accuracy preliminary triage, key information extraction, and intelligent scoring. The framework is domain-agnostic and successfully deployed across two heterogeneous programs: enterprise internationalization grants and residential energy-efficiency retrofit reimbursements. Experiments demonstrate a 20.1% improvement in review throughput for the reimbursement program, reducing end-to-end processing time by over two months, while maintaining near-zero false-positive rates. This work represents the first large-scale operational deployment of an LLM system in public fund auditing—balancing automation efficiency with auditable decision reliability—and establishes a reusable technical paradigm and empirically validated pathway for intelligent public financial governance.

Technology Category

• Natural Language Processing: (Large) Language Models
• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

Every year, the European Union and its member states allocate millions of euros to fund various development initiatives. However, the increasing number of applications received for these programs often creates significant bottlenecks in evaluation processes, due to limited human capacity. In this work, we detail the real-world deployment of AI-assisted evaluation within the pipeline of two government initiatives: (i) corporate applications aimed at international business expansion, and (ii) citizen reimbursement claims for investments in energy-efficient home improvements. While these two cases involve distinct evaluation procedures, our findings confirm that AI effectively enhanced processing efficiency and reduced workload across both types of applications. Specifically, in the citizen reimbursement claims initiative, our solution increased reviewer productivity by 20.1%, while keeping a negligible false-positive rate based on our test set observations. These improvements resulted in an overall reduction of more than 2 months in the total evaluation time, illustrating the impact of AI-driven automation in large-scale evaluation workflows.

Problem

• AI enhances efficiency in public funding application reviews
• LLMs reduce bottlenecks in government evaluation processes
• Automation cuts evaluation time for funding applications

Innovation

• Using LLMs to automate funding application reviews
• AI-assisted evaluation for government funding initiatives
• Boosting reviewer productivity while minimizing false positives