Metraipolis › archive › dc_bee1590bf665

EDU-Jev Training System-One Decision Models for Education — arXiv:2610.41079

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41079
License (as archived): CC0-1.0
Archived: 2026-11-02T07:03:42.622Z
SHA-256 of the archived text: fd21b04cbb6141228fe35e6f5e532542d05f7e5df0c0521e26d43504572f4443
Stable URL of this page: https://metraipolis.com/documento/dc_bee1590bf665

How to cite

EDU-Jev Training System-One Decision Models for Education — arXiv:2610.41079 — arXiv (en), https://arxiv.org/abs/2610.41079 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bee1590bf665 (Metraipolis archive dc_bee1590bf665, sha256 fd21b04cbb6141228fe35e6f5e532542d05f7e5df0c0521e26d43504572f4443)

BibTeX

@misc{dcbee1590bf665,
  title = {EDU-Jev Training System-One Decision Models for Education — arXiv:2610.41079},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41079},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bee1590bf665; sha256 fd21b04cbb6141228fe35e6f5e532542d05f7e5df0c0521e26d43504572f4443},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41079. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Many automated decisions in education involve choosing from a fixed set of options: assigning a rubric score, checking whether an answer meets a marking criterion, or identifying the first wrong step in a solution. Generative language models are increasingly used to make these decisions, but their responses require parsing, longer outputs increase inference costs, and confidence expressed in words does not necessarily reflect the probability of being correct. We present EDU-Jev, a family of single-pass ("System One") decision models at 0.8B, 2B and 4B parameters. Given an assessment context and a question with predefined answer options, the model returns a probability distribution over those options without generating text. A pointer head scores a marker for each option, ensuring the predictions are restricted to the allowed choices. Training uses a single supervised stage with soft cross-entropy against the available target label distributions; calibration is assessed empirically. Across twelve education benchmarks, EDU-Jev 4B achieves an average accuracy of 67.6%, exceeding the strongest of five commercial decision APIs by 9.4 percentage points and the best open 4B decision model by 18.7 points. On four cross-domain education sets, it matches the strongest API, which remains ahead on general decision-making and reasoning tasks. The 2B model processes about 150 decisions per second on a single H100 GPU.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.41079 — 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 2026-11-02T06:57:13.212Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).