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

arXiv: https://arxiv.org/abs/2605.05410 · HTML: https://mlsanity.com/paper/2605.05410/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 34 references that are in the map.
- First posted on arXiv 6 May 2026.

## Builds on (most cited first, 5 of 5)

- [Applying Large Language Models and Chain-of-Thought for Automatic Scoring](https://mlsanity.com/paper/2312.03748/) (2023)
- [Fine-tuning ChatGPT for Automatic Scoring](https://mlsanity.com/paper/2310.10072/) (2023)
- [Automatic assessment of text-based responses in post-secondary education: A systematic review](https://mlsanity.com/paper/2308.16151/) (2023)
- [Human-in-the-Loop Systems for Adaptive Learning Using Generative AI](https://mlsanity.com/paper/2508.11062/) (2025)
- [Auditing Student-AI Collaboration: A Case Study of Online Graduate CS Students](https://mlsanity.com/paper/2601.08697/) (2026)

## Abstract (arXiv)

Large-language-model (LLM) graders promise to relieve the grading burden of upper-division STEM courses, but most deployments to date send student work to third-party APIs, violating FERPA and exposing institutions to data risk while requiring substantial assignment modification. We present LaTA (textitLaTeX Teaching Assistant), a drop-in, open-source autograder that runs entirely on commodity on-premises hardware and assumes a LaTeX-native workflow already adopted by many engineering and physics courses. LaTA implements a four-stage pipeline (ingest, segment, grade, report) using a locally hosted open-weight chain-of-thought LLM grader (gpt-oss:120b) that compares student work to an instructor-authored reference solution and applies a YAML rubric with binary per-item scoring. We deployed LaTA in Winter~2026 in ME 373 (Mechanical Engineering Methods) at Oregon State University, grading every weekly assignment for approximately 200 students on a single Mac Studio at 0 marginal cost per assignment and 1--3 minutes of wall-clock time per submission, enabling regrading of corrected assignments and greatly expanded TA office hour offerings. The instructor-confirmed grading-error rate held at roughly 0.02--0.04% per rubric line item across the term. Relative to the same instructor's previous traditionally-graded cohort, the LaTA-graded cohort outperformed by approximately 11% on the midterm exam and 8% on the final exam, and reported large gains in self-assessed confidence on every stated learning objective (N = 159 survey responses, Delta ≥ +1.49 Likert points, p < 10-27 on every comparison). We release the code under AGPLv3.