Enhancing Living Standards Surveys in LMICs using Large Language Models скачать в хорошем качестве

Enhancing Living Standards Surveys in LMICs using Large Language Models

SoDa Symposium: Enhancing Living Standards Surveys in LMICs using Large Language Models A Presentation with Q&A Tuesday, February 24, 2026 12:00 pm - 1:00 pm EST Abstract: In low- and middle-income countries (LMICs), household surveys remain the main tools for understanding living standards, designing effective policies, and monitoring progress toward development goals. Household surveys are under pressure to deliver high-quality and comprehensive data in a timely manner within tightening budgets. The Living Standards Measurement Study (LSMS) - the World Bank’s flagship household survey program – has recently launched a multi-year program on innovations in survey measurement. The program is supporting the development and validation of enhanced survey methods and tools to increase the accuracy, timeliness and cost-effectiveness of surveys in LMICs, with a strong focus on mixed mode survey systems. The presentation will provide an overview of the LSMS workstream on AI which aims to improve key aspects of the survey process using large language models (LLMs) and generative AI. The work hinges on using interview transcripts for analysis in LLMs to (i) detect and reduce error in survey data and (ii) interpret open-ended survey responses and enabling simpler and more respondent-centric questionnaires without sacrificing analytical depth. The presentation will describe the key elements of the work program and the expected implementation challenges. Presented by: Philip Wollburg Senior Economist World Bank Philip Wollburg is a Senior Economist at the Survey Unit of the Development Data Group at the World Bank, based in Rome, Italy. He co-leads the program on Innovations in Survey Measurement of the Living Standards Measurement Study (LSMS), the World Bank’s flagship household survey program. His research focuses on agriculture, poverty, health, and the impacts of shocks, as well as measurement and survey methods. Philip was a core team member of the World Development Report 2021: Data for Better Lives, and prior to joining the World Bank, he worked with the Food and Agriculture Organization of the UN (FAO) and led a project aimed at delivering innovative renewable energy solutions to smallholder agricultural and fisheries communities in East Africa. He holds a PhD in Development Economics from Wageningen University.   Q & A Moderators: Amparo Palacios-Lopez Program Manager Survey Unit      Home of the International Comparison Program (ICP), Living Standards Measurement Study (LSMS) & Survey Solutions Development Data Group | World Bank | Washington, DC Talip Kilic Acting Manager and Senior Program Manager Survey Unit      Home of the International Comparison Program (ICP), Living Standards Measurement Study (LSMS) & Survey Solutions Development Data Group | World Bank | Washington, DC The SoDa Center at UMD SoDa Symposia highlight the diverse challenges and opportunities in the emerging area of Social Data Science.   Combining insights of SoDa researchers and partners from UMD and around the world, these regular virtual events showcase research and expert commentary about advances and open problems in the use of surveys, administrative, and trace data to understand and shape the social world we live in. Ranging from technical challenges of gathering high-quality data, ethical management of social data at scale, or examples of the power of social data science in education, business, government, or civic life, SoDa Symposia provide an opportunity for a broad audience of researchers, students, and practitioners to learn more about the potential of social data science to change the world.