In the field of natural language processing, the prevalent approach involves fine-tuning pretrained language models (PLMs) using local samples.

Accurately modeling weather variation pattern from large amount of meteorological variables sequences is increasingly vital for providing efficient weather analysis support for disaster warning.

By analyzing the intrinsic dimension (ID) and neighbor composition, we find that the representations evolve similarly in transformers trained on protein language tasks and image reconstruction tasks.

In this work, we conduct a pilot study showing that PLMs as few-shot learners are highly vulnerable to backdoor attacks while existing defenses are inadequate due to the unique challenges of few-shot scenarios.