← Voltar às notícias de pesquisa

#human-AI collaboration

human-AI collaboration

5 artigos

A lecturer and two design students compare a service storyboard with annotated feedback sheets while a student records revision ideas.
Artigo de conferência2025
Artigo de conferência 182

Students preferred AI design feedback in a small study, while improvements in design quality were not established

Tanja Katharina Schmitt-Fumian, Selina Tauscher, Katja Thoring

Proceedings of the Design Society (ICED25)

An ICED 25 study asked 25 students to compare GPT-4 feedback with comments from human educators on a design-ideation task. Students generally rated the AI comments more positively for support, clarity and organization. Feedback order was randomized, and interviews explored the reasons for preferences. The study measured reception of textual comments, not independently rated improvements in designs or later creative ability, and substantial prompt-development work preceded the comparison.

design educationformative feedbackhuman-AI collaboration
Ler resumo de 500 palavras →
Two design students compare an initial pull-along toy sketch with a revised axle drawing beside a small physical mock-up and laptop.
Artigo de revista2026
Artigo de revista 148

Thinking before consulting ChatGPT improved creativity on the next independent task

Sarah Shi Hui Wong, Sophia Xuefei Qiu

Educational Psychology Review

In a randomized experiment with 196 university students, unrestricted ChatGPT use improved an assisted product-design task but offered no advantage on the next unaided task. A guided group first generated its own ideas and then used ChatGPT to develop them; this group performed better independently afterward. The result supports investigating the sequence of human and AI work, while leaving delayed retention and the separate contribution of guidance unresolved.

human-AI collaborationcreativityindependent performance
Ler resumo de 500 palavras →
A writing tutor discusses two annotated drafts with a graduate student beside a laptop, with a sunlit Hong Kong waterfront visible through the window.
Artigo de revista2025
Artigo de revista 120

AI writing feedback improved revised drafts, while adding teacher feedback did not yield a clear overall advantage

Linqian Ding, Di Zou, Lucas Kohnke

Education and Information Technologies

A study of 77 graduate students in Hong Kong compared ChatGPT feedback with teacher-refined ChatGPT feedback on a literature-review assignment. Both groups improved their revised drafts. The combined approach produced a significant grammar advantage, but no significant overall improvement advantage between groups. Because the study assessed one assignment without an unaided transfer test, the findings concern revision quality rather than established long-term writing development.

academic writingfeedbackHong Kong
Ler resumo de 500 palavras →
A diverse group of educators reviews an instructional video storyboard, narration timeline, and multimedia-learning checks at a university media lab
Artigo de conferência2026
Artigo de conferência 110

Dual gatekeeping improved ratings of AI-generated instructional video without testing student learning

Yearim Kim, Njun Baek, Nojun Kwak

CHI 2026 Workshop on Understanding and Engaging Critical Resistance to AI in Education

Kim, Baek and Kwak present PedaCo, an AI-video workflow that lets educators revise scripts against multimedia-learning principles before synthesis and then checks the rendered video with automated pedagogical metrics. Twenty-three educators rated reviewed videos higher than baselines, while a 14-video comparison improved coherence and temporal alignment. The workshop study did not measure student learning or long-term teacher workload.

AI-generated videomultimedia learningeducator review
Ler resumo de 500 palavras →
A diverse group of university students and a lecturer examine clustered dialogue cards, a ten-trait matrix and an exam-progress chart in a bright learning analytics studio
Ferramenta / conjunto de dados2026
Ferramenta / conjunto de dados 94

Principal Trait Analysis linked AI-tutor dialogue patterns to outcomes, but not yet to transferable skills

Hunter McNichols, Kai Du, Andrew Lan

arXiv preprint

McNichols, Du and Lan introduce Principal Trait Analysis, an LLM-assisted pipeline that turns human-AI conversation traces into interpretable behavioral traits. On 1,540 university AI-tutor sessions and 2,774 professional coding-agent sessions, selected traits added explanatory or predictive signal beyond prior performance. Conceptual questioning aligned positively with some exam outcomes, but cross-semester inconsistency, contradictory coefficients and mostly flat temporal patterns mean the traits cannot yet be treated as transferable AI collaboration skills.

Principal Trait AnalysisAI tutoring dialoguehuman-AI collaboration
Ler resumo de 500 palavras →