作者位次 #4/8ACL 2026Poster· Natural Language Processing
Incomplete In-context Learning
wenqiang wang · Wen Yujia · Yan Xiao · Zhifeng Chen · Yangshijie Zhang · Peng Chen · Mingbo Yang · Xiaochun Cao
摘要
Existing In-context Learning (ICL) typically assumes the retrieval dataset contains demonstrations for all output label spaces. However, in real-world scenarios, delays in dataset updates or incomplete data annotation may result in the retrieval dataset containing labeled demonstrations for only...