Metraipolis › archive › dc_d4cc3c767faa

TutorCaseBench: A Case-Grounded Benchmark for Evaluating LLM Tutors in Supporting Students with Challenging Behaviors — arXiv:2610.30828

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.30828
License (as archived)
CC0-1.0
Archived
2026-10-23T15:20:30.572Z
SHA-256 of the archived text
bd35c6096653b76c49a86eb7e90c12bc91cdf24e3a27fc22c3bbd1a6181b05ed
Stable URL of this page
https://metraipolis.com/documento/dc_d4cc3c767faa

How to cite

TutorCaseBench: A Case-Grounded Benchmark for Evaluating LLM Tutors in Supporting Students with Challenging Behaviors — arXiv:2610.30828 — arXiv (en), https://arxiv.org/abs/2610.30828 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d4cc3c767faa (Metraipolis archive dc_d4cc3c767faa, sha256 bd35c6096653b76c49a86eb7e90c12bc91cdf24e3a27fc22c3bbd1a6181b05ed)
BibTeX
@misc{dcd4cc3c767faa,
  title = {TutorCaseBench: A Case-Grounded Benchmark for Evaluating LLM Tutors in Supporting Students with Challenging Behaviors — arXiv:2610.30828},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.30828},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d4cc3c767faa; sha256 bd35c6096653b76c49a86eb7e90c12bc91cdf24e3a27fc22c3bbd1a6181b05ed},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.30828. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLMs are increasingly used as AI tutors, yet existing benchmarks overlook the challenging behaviors common among students with learning and behavioral difficulties. We introduce TutorCaseBench, a benchmark that grounds AI-tutor evaluation in qualitative case studies from pedagogy, educational psychology, and special education. Our pipeline converts documented student categories into case-specific scenarios, tutor-student dialogues, and rubrics grounded in source evidence. The benchmark contains 923 dialogues across five challenge types, evaluated through open-ended response generation (1,560 items) and multiple-choice selection (2,537 items). Across 11 state-of-the-art LLMs, even the strongest model satisfies a rubric criterion in only 55.8% of open-ended cases, while models are better at selecting appropriate strategies than generating situated responses. These results reveal a gap between intervention recognition and context-specific adaptation, especially for open-weight models. All data are publicly available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2610.30828 — 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 2026-10-23T15:09:38.329Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).