Metraipolis › archive › dc_5ec27dcbcb6d

Rubric-Based Assessment of Student Reports Using Small Language Models — arXiv:2611.01785

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01785
License (as archived)
CC0-1.0
Archived
2026-11-03T18:24:38.116Z
SHA-256 of the archived text
f029346bdeb39cc54fc88e409b6da5758b553b7b2a01d15f0a62b12df834a126
Stable URL of this page
https://metraipolis.com/documento/dc_5ec27dcbcb6d

How to cite

Rubric-Based Assessment of Student Reports Using Small Language Models — arXiv:2611.01785 — arXiv (en), https://arxiv.org/abs/2611.01785 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5ec27dcbcb6d (Metraipolis archive dc_5ec27dcbcb6d, sha256 f029346bdeb39cc54fc88e409b6da5758b553b7b2a01d15f0a62b12df834a126)
BibTeX
@misc{dc5ec27dcbcb6d,
  title = {Rubric-Based Assessment of Student Reports Using Small Language Models — arXiv:2611.01785},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01785},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5ec27dcbcb6d; sha256 f029346bdeb39cc54fc88e409b6da5758b553b7b2a01d15f0a62b12df834a126},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01785. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Language models can analyze and assess student texts using predefined rubrics and deliver structured feedback, reducing instructors' workload. However, existing solutions often rely on external services that are resource-intensive, costly, and raise privacy concerns, making them unsuitable for constrained environments. This study evaluates an automated assessment pipeline with three key aims: design for low-resource environments, privacy, and focus on a novel context in cybersecurity education. The pipeline integrates lightweight language models for textual evaluation and a vision-language model for image interpretation. Responses from 105 students were collected over two semesters of an undergraduate course during a cybersecurity exercise on incident response. Results across different hardware configurations show that small models in low-resource environments can achieve up to 97% accuracy in text-only and up to 94% in rich-text assessments. This rivals or even outperforms a large model while adding the benefits of locally hosted assessment. Our solution can help educators and practitioners who need grading assistance without replacing human oversight, especially in environments where cloud-based solutions may be impractical. This study contributes an open-source, locally deployable AI-assisted scoring pipeline that runs on affordable hardware and can be extended to various types of student reports in computing education. As a result, it makes automated assessment accessible to a broad range of educators and institutions.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computers and Society (cs.CY) ; Computation and Language (cs.CL); Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2611.01785 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T18:10:08.039Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).