Metraipolis › archive › dc_467fefdda7ec

DICE: Decoupling Capability from Intervention Necessity in LLM Tutoring — arXiv:2610.04825

Source: arXiv
Original: https://arxiv.org/abs/2610.04825
License (as archived): CC0-1.0
Archived: 2026-10-06T05:24:49.839Z
SHA-256 of the archived text: 52263618eb671086b50ed29cf689dc7c11effdc078a29d26a0febe78bc468d0a
Stable URL of this page: https://metraipolis.com/documento/dc_467fefdda7ec

How to cite

DICE: Decoupling Capability from Intervention Necessity in LLM Tutoring — arXiv:2610.04825 — arXiv, https://arxiv.org/abs/2610.04825 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_467fefdda7ec (Metraipolis archive dc_467fefdda7ec, sha256 52263618eb671086b50ed29cf689dc7c11effdc078a29d26a0febe78bc468d0a)

BibTeX

@misc{dc467fefdda7ec,
  title = {DICE: Decoupling Capability from Intervention Necessity in LLM Tutoring — arXiv:2610.04825},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.04825},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_467fefdda7ec; sha256 52263618eb671086b50ed29cf689dc7c11effdc078a29d26a0febe78bc468d0a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04825. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Fluent guidance is not the same as useful intervention. LLM tutors are typically trained to generate the next teacher utterance, implicitly assuming that every student turn warrants a response. However, our experiments indicate that this conflates tutoring capability (what to say) with intervention necessity (whether to say it). We introduce DICE, a framework that decouples intervention decisions from response generation by first selecting an explicit pedagogical action. To calibrate this action selection policy, we define Intervention Value (IV), a rollout-grounded counterfactual metric that compares each action against non-intervention. IV shows that many prescribed interventions provide little or no marginal benefit. We further introduce DICE-Bench, a multi-variant math tutoring benchmark with skill-preserving problem variants for session-level evaluation. Using IV-weighted and KL-regularized policy optimization, DICE learns to intervene selectively while preserving tutoring effectiveness. In simulated tutoring sessions, DICE reduces the over-intervention rate to near zero while guiding students to correct solutions in approximately 3-4 fewer turns on average than existing Socratic tutoring baselines.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.04825 — 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 2026-10-06T05:24:05.523Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).