AfriEconQA: A Benchmark Dataset for African Economic Analysis based on World Bank Reports

TL;DR

AfriEconQA introduces a challenging dataset for African economic analysis, emphasizing high-precision reasoning over specialized reports, revealing significant gaps in current LLM capabilities for domain-specific IR tasks.

Contribution

This paper presents the first benchmark dataset focused on African economic analysis, designed to evaluate and improve IR and RAG systems in a domain with limited pretraining data.

Findings

Zero-shot models answer over 90% of queries incorrectly.

State-of-the-art RAG pipelines struggle with high-precision retrieval.

AfriEconQA is a robust benchmark highlighting knowledge gaps in current models.

Abstract

We introduce AfriEconQA, a specialized benchmark dataset for African economic analysis grounded in a comprehensive corpus of 236 World Bank reports. The task of AfriEconQA is to answer complex economic queries that require high-precision numerical reasoning and temporal disambiguation from specialized institutional documents. The dataset consists of 8,937 curated QA instances, rigorously filtered from a pool of 10018 synthetic questions to ensure high-quality evidence-answer alignment. Each instance is composed of: (1) a question requiring reasoning over economic indicators, (2) the corresponding evidence retrieved from the corpus, (3) a verified ground-truth answer, and (4) source metadata (e.g., URL and publication date) to ensure temporal provenance. AfriEconQA is the first benchmark focused specifically on African economic analysis, providing a unique challenge for Information Retrieval (IR) systems, as the data is largely absent from the pretraining corpora of current Large Language Models (LLMs). We operationalize this dataset through an 11-experiment matrix, benchmarking a zero-shot baseline (GPT-5 Mini) against RAG configurations using GPT-4o and Qwen 32B across five distinct embedding and ranking strategies. Our results demonstrate a severe parametric knowledge gap, where zero-shot models fail to answer over 90 percent of queries, and even state-of-the-art RAG pipelines struggle to achieve high precision. This confirms AfriEconQA as a robust and challenging benchmark for the next generation of domain-specific IR and RAG systems. The AfriEconQA dataset and code will be made publicly available upon publication.