3 papers
cs.DB2025
DRAMA: Unifying Data Retrieval and Analysis for Open-Domain Analytic Queries
Chuxuan Hu, Maxwell Yang, James Weiland +3
Manually conducting real-world data analyses is labor-intensive and inefficient. Despite numerous attempts to automate data science workflows, none of the existing paradigms or sys…
cs.CL2025
REPRO-Bench: Can Agentic AI Systems Assess the Reproducibility of Social Science Research?
Chuxuan Hu, Liyun Zhang, Yeji Lim +3
Assessing the reproducibility of social science papers is essential for promoting rigor in research processes, but manual assessment is costly. With recent advances in agentic AI s…
cs.DB2025
LEAP: LLM-powered End-to-end Automatic Library for Processing Social Science Queries on Unstructured Data
Chuxuan Hu, Austin Peters, Daniel Kang
Social scientists are increasingly interested in analyzing the semantic information (e.g., emotion) of unstructured data (e.g., Tweets), where the semantic information is not nativ…