EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

LLM-Supported Hybrid Rubric Assessment in Multi-Stage Algebraic Block Coding Tasks: Design and Initial Evaluation

Yong Oh Lee, Byeonghun Bang, Sejun Oh

Applied Sciences · 26.10.2026 · 16 (21) · 10595

DOI: 10.3390/app162110595 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 26.10.2026. Verfasst von Yong Oh Lee und 2 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korea Foundation for the Advancement of Science and Creativity.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Assessment of multi-stage mathematics tasks requires explicit links between student work and evaluation criteria. This study presents a large language model (LLM)-supported hybrid rubric framework combining rule-based correctness checks, categorical evaluation of task-segment evidence, and separate qualitative feedback generation. Its task-specific profile distinguishes conceptual understanding, symbolic procedures, block-coding procedures, self-reported persistence, and a written explanation of tool usefulness. An initial evaluation involved 42 middle-school students undertaking a quadratic-equation task. Two experts independently scored student work without access to system scores; averaged ratings for 40 students yielded 200 paired rubric scores. System and expert scores showed moderate association (Pearson correlation = 0.632; Spearman rank correlation = 0.676), with a mean absolute error of 17.3 points and mean bias of +5.1 points. Learner-cluster bootstrap intervals accounted for scores nested within students. Excluding self-reported persistence yielded 160 pairs, a Pearson correlation of 0.669, and a mean absolute error of 16.8. Block-coding scores showed the strongest association with expert scores, while symbolic-procedure scores had the smallest absolute errors. Individual score differences were substantial. The study provides a task-specific design and an initial empirical reference for developing teacher-supervised hybrid assessment.

Förderung

  • Korea Foundation for the Advancement of Science and Creativity

Zitieren

APA

Lee, Y. O., Bang, B., & Oh, S. (2026). LLM-Supported Hybrid Rubric Assessment in Multi-Stage Algebraic Block Coding Tasks: Design and Initial Evaluation. Applied Sciences, 16(21), 10595. https://doi.org/10.3390/app162110595

Vancouver

Lee YO, Bang B, Oh S. LLM-Supported Hybrid Rubric Assessment in Multi-Stage Algebraic Block Coding Tasks: Design and Initial Evaluation. Applied Sciences. 2026;16(21):10595. doi:10.3390/app162110595

BibTeX
@article{Lee2026,
  author = {Lee, Yong Oh and Bang, Byeonghun and Oh, Sejun},
  title = {LLM-Supported Hybrid Rubric Assessment in Multi-Stage Algebraic Block Coding Tasks: Design and Initial Evaluation},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {21},
  pages = {10595},
  doi = {10.3390/app162110595}
}
Kostenlos starten →