.png){kind=icon}
.png){kind=icon}
Return
LaQual: An automated framework for LLM app quality evaluation
.png){kind=icon}
PRE
AI
Y
X
J
Y
W
H
DOI：10.1016/j.jss.2026.112997.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• We propose LaQual, an automated framework for fine-grained LLM app evaluation. • A time-decay weighting mechanism is introduced to mitigate temporal ranking bias. • LLMs adaptively generate scenario-specific metrics and tasks for evaluation. • Automated scores achieve high consistency with expert judgment across categories. • User studies confirm significant gains in decision efficiency and confidence.
Journal
IF:
4.1
Papers:
5.4K
Citations:
8.4K
Organization
Cited Papers