04:00
2026-08-28
arxiv.org
artificial-intelligence
Interpretable, Fairly Evaluated Automated L2 Speaking Assessment that Beats the Single-Human Ceiling and Why Pause Encoding Does Not Change LLM Fluency Scores
A new hybrid scoring system for automated second-language speaking assessment, combining interpretable speech-timing features with a text-LLM fluency judgment, achieved a Spearman rho of 0.818 against…