NAISS
SUPR
NAISS Projects
SUPR
Distilling a math-feedback LLM
Dnr:

NAISS 2026/4-815

Type:

NAISS Small

Principal Investigator:

Alexandros Sopasakis

Affiliation:

Lunds universitet

Start Date:

2026-04-28

End Date:

2026-06-01

Primary Classification:

10208: Natural Language Processing

Webpage:

Allocation

Abstract

We build a local, privacy-preserving language model giving live formative feedback on undergraduate math coursework. A strong open teacher model (e.g. Qwen2.5-Math) is distilled into a compact 3–7B student running on-prem for GDPR-compliant, low-latency use. Students receive structured hints and Socratic type step-gating; teachers get dashboards surfacing recurring misconceptions. Outputs: working model, inference script, guidelines, evaluation report.