Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization
Taesun Yeom · Taehyeok Ha · Jaeho Lee
首次获取该候选人的完整档案及 StartLux 评估共 20 积分;每位用户单独解锁,之后查看免费。主动刷新 20 积分。
实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。
Taesun Yeom · Taehyeok Ha · Jaeho Lee
Hyunjong Ok · Suho Yoo · Jaeho Lee
Spoken dialogue systems powered by large language models have demonstrated remarkable abilities in understanding human speech and generating appropriate spoken responses.However, these systems struggle with end-turn detection (ETD)—the ability to distinguish between user turn completion and hesit...
Hyunjong Ok · Jaeho Lee
Large language models exhibit surprising sensitivity to the structure of the prompt, but the mechanisms underlying this sensitivity remain poorly understood. In this work, we conduct an in-depth investigation on a striking case: in multiple-choice question answering, placing context before the qu...