LaTA: A Drop-in, FERPA-Compliant Local-LLM Autograder for Upper-Division STEM Coursework

Created: 2026-05-15 | Tags: automated-gradinghigher-edstem-educationllmgenerative-aiefficacy-studyfeedback-loop

LaTA: A Drop-in, FERPA-Compliant Local-LLM Autograder for Upper-Division STEM Coursework RodrΓ­guez (2026) β€” Oregon State University. Submitted to Computers & Education. πŸ“„ Full text (arXiv)

Summary

LaTA (LaTeX Teaching Assistant) is a privacy-preserving, drop-in autograder that addresses the core tension in educational LLM deployment: most automated-grading systems send student work to third-party APIs, violating FERPA and exposing institutions to data risk.

System architecture:

Real-world deployment (Winter 2026):

Learning outcomes (vs. traditional cohort):

These results provide strong evidence for the feedback-loop hypothesis: faster, more consistent feedback drives both learning and confidence. The deployment demonstrates that generative-ai grading can be both FERPA-compliant and pedagogically effective, addressing concerns raised in assessment-validity and formative-assessment discussions.

LaTA's success connects to the broader stem-education and higher-ed landscape, showing that llm-based grading can move beyond short-answer-scoring-quality-degradation concerns when properly designed with instructor-authored rubrics and reference solutions. The open-source, zero-marginal-cost model aligns with principled-ai-education principles.

Related Pages

Citation

APA: RodrΓ­guez, J. A. (2026). LaTA: A drop-in, FERPA-compliant local-LLM autograder for upper-division STEM coursework. arXiv:2605.05410. Submitted to Computers & Education.