Automating Evidence Synthesis: A Comparative Evaluation of Large Language Models for Data Extraction
https://d.repec.org/n?u=RePEc:ris:adbewp:022484&r=&r=big
Published: May 15, 2026 00:00
Systematic reviews and meta-analyses (SRMAs) are important tools for evidence synthesis but have historically required substantial manual effort, particularly during the data extraction phase. To address this bottleneck, we developed and evaluated an…
Monitoring global trade by products, using Big Data
https://d.repec.org/n?u=RePEc:oec:stdaaa:2026/02-en&r=&r=big
Published: May 6, 2026 00:00
This paper develops a novel methodology to derive timely, experimental estimates of trade by commodity with global coverage using messages from the Automatic Identification System (AIS). By transforming high-frequency vessel movements into trade proxies,…
SynPop-DE: Synthetic population of 40 million German households using generative neural networks
https://d.repec.org/n?u=RePEc:osf:socarx:zha8v_v1&r=&r=big
Published: April 12, 2026 00:00
Household microdata combining socio-demographic, housing, income and expenditure attributes are a core resource for many studies in quantitative social science, such as modelling the household-level impacts of the energy transition. Yet no such data are…
Machine Learning Approaches for Improving Demand Forecasting Accuracy in Retail Supply Chains
https://d.repec.org/n?u=RePEc:osf:socarx:4z9be_v1&r=&r=big
Published: April 3, 2026 00:00
Accurate demand forecasting remains one of the most critical yet persistently challenging functions in retail supply chain management. Traditional statistical forecasting methods such as ARIMA and exponential smoothing have long served as industry…
Validating Large Language Model Annotations
https://d.repec.org/n?u=RePEc:fip:fedgfe:103001&r=&r=big
Published: March 30, 2026 00:00
This paper proposes a validation framework for LLM-generated measurements when reliable benchmarks are unavailable. Validity is established by testing whether an LLM can reconstruct passages from annotated labels while maintaining semantic consistency with…