Retrieval Challenges in Low-Resource Public Service Information: A Case Study on Food Pantry Access

2026-02-25

AI Summary

This work addresses the challenge of retrieving critical public resources—such as food distribution sites—in low-resource settings, where fragmented, inconsistently formatted, and outdated information impedes effective access. The paper presents the first AI-driven conversational retrieval system tailored to such environments, integrating web crawling, information indexing, and retrieval-augmented generation (RAG) to support natural language queries. Through a pilot evaluation using real community queries, the study systematically examines core challenges in conversational retrieval, including robustness, handling of ambiguous queries, and factual consistency under knowledge base inconsistencies. The findings reveal significant limitations of current approaches in real-world deployment scenarios, offering empirical insights and research directions to enhance the accessibility and reliability of public services.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: Conversational AI/Dialog Systems
• Knowledge Representation and Reasoning: Common-Sense Reasoning

Application Category

• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Web Mining and Content Analysis: Community question answering

Abstract

Public service information systems are often fragmented, inconsistently formatted, and outdated. These characteristics create low-resource retrieval environments that hinder timely access to critical services. We investigate retrieval challenges in such settings through the domain of food pantry access, a socially urgent problem given persistent food insecurity. We develop an AI-powered conversational retrieval system that scrapes and indexes publicly available pantry data and employs a Retrieval-Augmented Generation (RAG) pipeline to support natural language queries via a web interface. We conduct a pilot evaluation study using community-sourced queries to examine system behavior in realistic scenarios. Our analysis reveals key limitations in retrieval robustness, handling underspecified queries, and grounding over inconsistent knowledge bases. This ongoing work exposes fundamental IR challenges in low-resource environments and motivates future research on robust conversational retrieval to improve access to critical public resources.

Problem

• low-resource retrieval
• public service information
• food pantry access
• information fragmentation
• retrieval challenges

Innovation

• low-resource retrieval
• conversational retrieval
• Retrieval-Augmented Generation (RAG)
• public service information
• food pantry access