Archiving this opportunity has collateral effects. If you archive this opportunity, 14 active application(s) will be archived. Archived applications cannot be managed by Program Officers, and they cannot be viewed or managed by applicants.
Students have the opportunity to engage in world-class research that has real-world impact. Undergraduate student research fellows are paid $19/hour*. Students must be enrolled full-time to participate and must be able to commit to research 8-10 hours per week.
*Students must attend orientation and submit an I-9 form to verify employment and receive payment.
Research Project Description:
Systematic reviews of health and development research are resource- and labor-intensive, and a cornerstone of scientific evidence. These comprehensive studies, which typically take months to complete, can now potentially be carried out in mere hours without compromising on their precision and rigor.
We are developing an LLM-assisted pipeline for systematic reviews that could save significant time and resources for researchers, policy makers, healthcare and commercial entities.
Systematic reviews currently depend on scientifically literate human resources to screen articles and extract data. These tasks are particularly well-suited for large language models. To streamline this process, we broke down the PRISMA guidelines (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) into smaller, resource-intensive tasks that are particularly well-suited for LLMs. By ensuring the process is rigorous, grounded, and trustworthy, we are differentiating our tool from existing AI-based research tools.
We are looking for data science, CS, or CS-adjacent students interested in health and development to join our Gates-funded project. We are looking for students with expertise in systems, user interface, or database design.
Primary Research Mentor: Eran Bendavid, Professor - School of Medicine
What you will do
Design tool evaluation protocol
Program evaluation pipeline
Improve evidence synthesis risk of bias tools
Eligibility and Requirements:
Stanford undergraduate students in good academic standing and enrolled full-time are eligible to apply. Co-term students must have undergraduate student status; if co-terms are in graduate billing status (after 12 quarters) they are ineligible to participate.
All majors are welcome!
Students Responsibilities:
Specific tasks related to our pipeline: - Design tool evaluation protocol - Program evaluation pipeline - Improve evidence synthesis risk of bias tools
Students qualifications:
We are looking for data science, CS, or CS-adjacent students with good Python skills and an ability to work well in teams
Time Commitment:
The time commitment is 8-10 hours per week (equivalent to a 3-unit course) each academic quarter. The expectation is that students will work the full academic year with their mentor (Autumn, Winter, and Spring quarters). Students planning on studying abroad are not eligible.
To Apply:
Along with the application, applicants are asked to submit:
a cover letter
resume or CV
unofficial Stanford transcript (first quarter frosh do not need to submit transcripts for autumn quarter applications)
Research Mentor Questions for Applicants: Do you have experience with any of the following, if so please describe: