AIEDHK
← 返回研究新闻

#large language models

large language models

2 篇论文

A child-safety research team studies branching multi-turn dialogue traces behind a protected classroom observation window without showing harmful content
会议论文2025
会议论文 66

Child-specific multi-turn red teaming found safety gaps that adult baselines and single-turn tests missed

Prasanjit Rath, Hari Shrawgi, Parag Agrawal, Sandipan Dandapat

NAACL 2025 Industry Track

Rath and colleagues created 560 synthetic child personas and matched adult baselines to red-team six language-model snapshots over five-turn conversations. The benchmark found substantially higher defect rates for child scenarios in several categories and showed that many failures emerged only after the dialogue developed.

child safetylarge language modelsred teaming
阅读 500 字摘要 →
Student and teacher balancing learning support with privacy risks while reviewing large-language-model output
综述2023
综述 02

ChatGPT for good? On opportunities and challenges of large language models for education

Enkelejda Kasneci, Kathrin Sessler, Stefan Kuechemann, Maria Bannert, Daryna Dementieva, Frank Fischer, Urs Gasser, Georg Groh, Stephan Guennemann, Eyke Huellermeier, Stephan Krusche, Gitta Kutyniok, Tilman Michaeli, Claudia Nerdel, Juergen Pfeffer, Oleksandra Poquet, Michael Sailer, Albrecht Schmidt, Tina Seidel, Matthias Stadler, Jochen Weller, Jochen Kuehn, Gjergji Kasneci

Learning and Individual Differences

A widely cited position paper that balances the educational opportunities of large language models with risks around bias, privacy, assessment, and teacher guidance.

large language modelsChatGPTteacher support
阅读 500 字摘要 →