Meng-Jie Qian

This work investigates parameter-efficient approaches for transferring knowledge from resource-rich source languages to low-resource target languages on Whisper, and proposes Sequential Adapter Stacking, which places a trainable target-language adapter on top of a frozen source-language adapter.

Concept recoverability in AI grading systems varies significantly by architecture, revealing hidden biases that could undermine assessment fairness.

LLMs aren't equally reliable as NLG evaluators, but a Bradley-Terry extension called BT-sigma can learn judge reliability from pairwise comparisons alone, improving ranking accuracy without human supervision.