EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PrivPath: Privacy-Preserving Teaching-Path Guidance via Stage–Subject–Textbook Aligned Large Language Models

Shiming Fu, Haixia Wu, Jie Zhou, Zijie Pan

Mathematics · 14.04.2026 · 14 (8) · 1306

DOI: 10.3390/math14081306 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematics, online erschienen am 14.04.2026. Verfasst von Shiming Fu und 3 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large language models (LLMs) offer new opportunities for lesson planning, remediation, and personalized practice, but deploying them in real educational settings remains challenging for two reasons. First, direct use of learner interaction traces can expose sensitive information about student knowledge states and behavioral patterns. Second, unconstrained generation can produce recommendations that are pedagogically inconsistent with the adopted curriculum, such as skipping prerequisite concepts or drifting outside the prescribed textbook scope. We propose PrivPath, a stage–subject–textbook-aligned framework for privacy-preserving curriculum planning that explicitly separates on-device learner modeling from server-side content generation. Its core module, Tri-Index Private Path Planning (TIPP), first restricts planning to a scoped curriculum graph defined by the target educational context, then privatizes learner mastery summaries under local differential privacy before transmission, and finally computes a curriculum-feasible instructional path that is coupled with evidence-grounded constrained generation. This design preserves personalization while reducing reliance on raw student traces and improving controllability of the generated teaching sequence. Experiments on three educational interaction datasets paired with open-textbook curriculum graphs show that PrivPath substantially improves structural validity and privacy robustness. In particular, it raises graph feasibility from 82.5% to 99.2% relative to TriIndex-RAG, improves the offline pedagogical utility proxy ΔAUC from 0.013 to 0.018, and lowers membership inference AUC from 0.74 to 0.52 at εloc=1.0. These results suggest that curriculum-aligned path planning, privacy-preserving learner adaptation, and practically useful LLM-based educational generation can be achieved within a unified framework.

Zitieren

APA

Fu, S., Wu, H., Zhou, J., & Pan, Z. (2026). PrivPath: Privacy-Preserving Teaching-Path Guidance via Stage–Subject–Textbook Aligned Large Language Models. Mathematics, 14(8), 1306. https://doi.org/10.3390/math14081306

Vancouver

Fu S, Wu H, Zhou J, Pan Z. PrivPath: Privacy-Preserving Teaching-Path Guidance via Stage–Subject–Textbook Aligned Large Language Models. Mathematics. 2026;14(8):1306. doi:10.3390/math14081306

BibTeX
@article{Fu2026,
  author = {Fu, Shiming and Wu, Haixia and Zhou, Jie and Pan, Zijie},
  title = {PrivPath: Privacy-Preserving Teaching-Path Guidance via Stage–Subject–Textbook Aligned Large Language Models},
  journal = {Mathematics},
  year = {2026},
  volume = {14},
  number = {8},
  pages = {1306},
  doi = {10.3390/math14081306}
}
Kostenlos starten →