Junfeng Jiao
Titles as the sources gave them. In 1 entry, with 2 checked quotations.
What they said
Newest first. Each quotation was found word for word in the source.
“We find that harm concentrates in representational, dignity-related, and psychological categories, and co-occurs most often with deployment-context, governance, and misuse failures rather than model defects.”
“These findings suggest that model-level evaluations, while necessary, cannot by themselves anticipate the harm pathways most often documented for children.”
In the Base
Every entry they appear in.
Safe by Benchmark, Unsafe in Practice: Lessons from 1331 Child-Related AI Incidents
In an arXiv preprint, Junfeng Jiao and six co-authors code 1331 publicly reported child-related AI incidents into a child-centered harm taxonomy. They argue model-level safety tests cannot by themselves anticipate the harm pathways most often documented for children, and propose measures beyond content filtering.