Leverage a Large Language Model to automatically apply certain categories to content being posted to ReliefWeb - https://reliefweb.int/. The intention is to reduce human efforts in areas that where AI can provide a suitable solution thereby allowing our human capacity to focus on more impactful activities. We are using LLM without any fine-tuning as we have found the results to be more than sufficient ‘as is’.
Activity Type AI Tools/SolutionsWe’ve developed an AI summarization tool using Microsoft Azure OpenAI for the United Nations’ Central Emergency Response Fund (CERF). This tool efficiently processes Microsoft Word project proposals, extracting relevant information from various sections to generate a three-sentence project summary. Traditionally, CERF program officers manually crafted these summaries, which consumed approximately 5 minutes each. Our tool, however, produces accurate summaries within seconds. Given the volume of over 500 CERF projects annually, this tool stands to save more than 40 hours of staff time per year—a significant efficiency gain.
Activity Type AI Tools/SolutionsThe Ask ReliefWeb Q&A Chatbot allows a site visitor to ask questions about the (single) report page that they are viewing. On average, a single report had an attached file of approximately 17 pages. The Q&A Chatbot retrieves answers from that material.
Activity Type AI Tools/SolutionsThis project aims to identify the potential of having a chatbot that can answer questions based on all data collected by the Data Aggregation and Visualization Service (DAVIS). The project is currently in the design phase and undergoing a pivot with subsets of information to leverage the capacity.
Activity Type AI Tools/Solutions