RescueLens: LLM-Powered Triage and Action on Volunteer Feedback for Food Rescue

2025-11-19

AI Summary

Food rescue organizations rely on volunteer feedback to identify operational issues and ensure service quality, yet manual feedback processing suffers from low efficiency and delayed response times. This paper introduces the first large language model (LLM)-driven intelligent feedback processing framework tailored to food rescue operations, enabling three core capabilities: (1) automated text classification and issue severity grading; (2) identification and prioritization of critical donors/recipients; and (3) dynamic updating of volunteer guidance. Trained and fine-tuned on a real-world annotated dataset, the framework achieves 96% issue recall and 71% classification accuracy in production deployment. Notably, it precisely identifies high-frequency anomalous donors—constituting only 0.5% of the donor population yet responsible for over 30% of volunteer-reported issues. To our knowledge, this is the first systematic application of LLMs to feedback governance in food rescue, significantly improving response latency, decision-making accuracy, and volunteer satisfaction.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: AI for Accessibility

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Food rescue organizations simultaneously tackle food insecurity and waste by working with volunteers to redistribute food from donors who have excess to recipients who need it. Volunteer feedback allows food rescue organizations to identify issues early and ensure volunteer satisfaction. However, food rescue organizations monitor feedback manually, which can be cumbersome and labor-intensive, making it difficult to prioritize which issues are most important. In this work, we investigate how large language models (LLMs) assist food rescue organizers in understanding and taking action based on volunteer experiences. We work with 412 Food Rescue, a large food rescue organization based in Pittsburgh, Pennsylvania, to design RescueLens, an LLM-powered tool that automatically categorizes volunteer feedback, suggests donors and recipients to follow up with, and updates volunteer directions based on feedback. We evaluate the performance of RescueLens on an annotated dataset, and show that it can recover 96% of volunteer issues at 71% precision. Moreover, by ranking donors and recipients according to their rates of volunteer issues, RescueLens allows organizers to focus on 0.5% of donors responsible for more than 30% of volunteer issues. RescueLens is now deployed at 412 Food Rescue and through semi-structured interviews with organizers, we find that RescueLens streamlines the feedback process so organizers better allocate their time.

Problem

• Automating manual volunteer feedback analysis for food rescue organizations
• Prioritizing critical issues from volunteer reports using LLM technology
• Streamlining organizer follow-up actions on donor and recipient problems

Innovation

• LLM-powered tool categorizes volunteer feedback automatically
• Suggests donors and recipients for follow-up actions
• Updates volunteer directions based on feedback analysis