A shared vocabulary, a design space, and evidence that measured monitoring and task performance are separable design targets are contributed, suggesting that measured monitoring and task performance are separable design targets.
Abstract
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.
These findings show why AI-supported learning requires interaction records to provide a more defensible basis for AI-supported designs than self-reports.
Fatima T. Zahra, Wei Wang, Frances K. Harper et al.· arXiv.org· 0 citations
It is suggested that while explainable ChatGPT effectively strengthens the understanding of specific, explained content, it does not confer immediate, generalized gains in metacognitive abilities or holistic writing outcomes.
Mohammad Mousazadeh· International Journal of Eng...· 0 citations
Evaluating LLMs in interaction with humans and designing support for selective deference that preserves independent reasoning motivate evaluating LLMs in interaction with humans.
Robin Welsch, Michelle Rausch, Pascal Knierim et al.· arXiv.org· 0 citations
CoMeT matched the question-only tutor's demand, delivered artifacts twice as often as the assistant, and frustrated learners less than the question-only tutor, with delegation and load unchanged.
Xin-Meng Hou, Yuxuan Weng, Chin-Hsien Yeh et al.· 0 citations
Collaborative academic reading depends on coordination that existing tools do not provide. Readers need to know when peers are confused, who can help, and when AI assistance would add value rather than interrupt. Two interaction problems remain unresolved: when AI should intervene (grounded in sustained behavioural sig...
Sakil Sarker, Yasaman A. Basti, Heidar Davoudi et al.· 0 citations
Known for his clear and elegant writing style, Bertsekas shaped fields from control and optimization to large-scale computation and artificial intelligence.
MIT News · Artificial Intelligence· news.mit.eduJul 7, 2026
The professor of physics and inaugural director of the NSF AI Institute for Artificial Intelligence and Fundamental Interactions will lead LNS and continue his research in particle physics.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.