GRASP: Municipal Budget AI Chatbots for Enhancing Civic Engagement

2024-12-15

BigData Congress [Services Society]

AI Summary

This study addresses low municipal budget information accessibility and high public comprehension barriers, which hinder civic engagement and constrain governmental transparency. To tackle these challenges, we propose a novel AI chatbot framework integrating Retrieval-Augmented Generation (RAG) with a multi-step agent workflow. Our approach innovatively constructs a structured municipal budget knowledge base, incorporates domain-specific prompt engineering, and embeds collaborative verification by frontline government officials—establishing a closed-loop “Generate–Retrieve–Act–Verify” process. Evaluated on local budget question-answering tasks, our system achieves 78% accuracy, substantially outperforming GPT-4o (60%) and Gemini (35%). The framework effectively lowers the cognitive barrier to fiscal information, enhances the quality of public participation, and delivers a reusable technical pathway and practical paradigm for advancing transparency in grassroots fiscal governance in the digital era.

Technology Category

• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy
• Humans and AI: AI for Accessibility
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

There are a growing number of AI applications, but none tailored specifically to help residents answer their questions about municipal budget, a topic most are interested in but few have a solid comprehension of. In this research paper, we propose GRASP, a custom AI chatbot framework which stands for Generation with Retrieval and Action System for Prompts. GRASP provides more truthful and grounded responses to user budget queries than traditional information retrieval systems like general Large Language Models (LLMs) or web searches. These improvements come from the novel combination of a Retrieval-Augmented Generation (RAG) framework ("Generation with Retrieval") and an agentic workflow ("Action System"), as well as prompt engineering techniques, the incorporation of municipal budget domain knowledge, and collaboration with local town officials to ensure response truthfulness. During testing, we found that our GRASP chatbot provided precise and accurate responses for local municipal budget queries 78% percent of the time, while GPT-4o and Gemini were only accurate 60% and 35% of the time, respectively. GRASP chatbots greatly reduce the time and effort needed for the general public to get an intuitive and correct understanding of their town’s budget, thus fostering greater communal discourse, improving government transparency, and allowing citizens to make more informed decisions.

Problem

• Develops AI chatbot for municipal budget queries
• Improves response accuracy over general LLMs
• Enhances civic engagement and government transparency

Innovation

• Retrieval-Augmented Generation framework for accuracy
• Agentic workflow enhances response truthfulness
• Domain-specific prompt engineering for municipal budgets