Metraipolis › archive › dc_ddc8eccd362d

A Unified Response Framework for Questions and Tutoring Dialogues — arXiv:2610.19532

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.19532
License (as archived): CC0-1.0
Archived: 2026-10-15T14:23:25.026Z
SHA-256 of the archived text: ca4855914e0ea6426501aa1716304e2e33ff8690d37649fbb3059f1cbb61e9d6
Stable URL of this page: https://metraipolis.com/documento/dc_ddc8eccd362d

How to cite

A Unified Response Framework for Questions and Tutoring Dialogues — arXiv:2610.19532 — arXiv (en), https://arxiv.org/abs/2610.19532 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ddc8eccd362d (Metraipolis archive dc_ddc8eccd362d, sha256 ca4855914e0ea6426501aa1716304e2e33ff8690d37649fbb3059f1cbb61e9d6)

BibTeX

@misc{dcddc8eccd362d,
  title = {A Unified Response Framework for Questions and Tutoring Dialogues — arXiv:2610.19532},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.19532},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ddc8eccd362d; sha256 ca4855914e0ea6426501aa1716304e2e33ff8690d37649fbb3059f1cbb61e9d6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19532. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Existing student models in educational applications largely focus on student responses to questions. However, as tutoring becomes more accessible at large scale, it is important to analyze dialogues between tutors and students, which may reveal fine-grained evidence on student knowledge. In this work, we propose a unified framework that models both student responses to questions and tutor-posed subtasks during dialogues on a shared item response theory (IRT) scale. We first identify mathematical subtasks in tutoring dialogues, rewrite them into self-contained questions, and identify the correctness of student responses to these subtasks. We then develop an IRT framework that estimates question/subtask difficulty from text, tracks students' evolving abilities across question-answering and dialogue interactions, and a novel method to leverages tutor moves between consecutive subtasks to regularize their difficulty values. We evaluate our framework on two real-world math education datasets containing both human- and AI-tutored dialogues. Results show that our framework outperforms strong baselines on both question difficulty prediction and response correctness prediction.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Computers and Society (cs.CY); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.19532 — 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 2026-10-15T13:53:35.866Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).