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

TL;DR

This paper explores retrieval challenges in low-resource public service information systems, focusing on food pantry access, and presents an AI-powered conversational retrieval system to improve access despite data inconsistencies.

Contribution

It introduces a novel retrieval system using RAG for low-resource public service data and analyzes its limitations in real-world scenarios.

Findings

System faces robustness issues with underspecified queries

Handling inconsistent data remains a major challenge

Highlights need for more resilient retrieval methods in low-resource settings

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Public service information systems are often fragmented, inconsistently formatted, and outdated.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.