Metraipolis › archive › dc_e4bea529e909

Beyond "ChatGPT Can Make Mistakes": Designing Interventions to Support Metacognitive Monitoring in AI-Assisted Work — arXiv:2609.17065

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.17065
License (as archived)
CC0-1.0
Archived
2026-10-15T18:38:48.236Z
SHA-256 of the archived text
fbc76173e8afd49b6a0afba902a24c9a8b9053455e912c0730db242b10837699
Stable URL of this page
https://metraipolis.com/documento/dc_e4bea529e909

How to cite

Beyond "ChatGPT Can Make Mistakes": Designing Interventions to Support Metacognitive Monitoring in AI-Assisted Work — arXiv:2609.17065 — arXiv (en), https://arxiv.org/abs/2609.17065 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e4bea529e909 (Metraipolis archive dc_e4bea529e909, sha256 fbc76173e8afd49b6a0afba902a24c9a8b9053455e912c0730db242b10837699)
BibTeX
@misc{dce4bea529e909,
  title = {Beyond "ChatGPT Can Make Mistakes": Designing Interventions to Support Metacognitive Monitoring in AI-Assisted Work — arXiv:2609.17065},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.17065},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e4bea529e909; sha256 fbc76173e8afd49b6a0afba902a24c9a8b9053455e912c0730db242b10837699},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.17065. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AI assistance places a metacognitive demand on users, who must judge their own competence and the system's. Yet designers lack comparative evidence on which interventions to choose, where to place them, and how to tell whether they worked. We elicited 30 interventions from 11 experts and, with prior work, organized them into a design space of time (when an intervention acts), level (whose competence is judged), and source (who supplies the monitoring cue). A between-subjects experiment (N = 917; 12 planning-and-organizing problems) compared a per-task reliability card, contrasting replies, pause points, and post-problem reflection against a baseline LLM assistant. Reliability cards and contrasting replies reduced estimation error and overconfidence and increased aggregate confidence discrimination. No task-performance improvement or average within-item discrimination gain was established. We contribute a shared vocabulary, a design space, and evidence that measured monitoring and task performance are separable design targets.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.AI).
Categorie arXiv: Human-Computer Interaction (cs.HC) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.17065 — 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 2026-10-15T18:03:09.721Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).