CrossTune: Black-Box Few-Shot Classification with Label Enhancement

arXiv:2403.12468v1 Announce Type: new
Abstract: Training or finetuning large-scale language models (LLMs) requires substantial computation resources, motivating recent efforts to explore parameter-efficient adaptation to downstream tasks. One approach is to treat these models as black boxes and use forward passes (Inference APIs) to interact with them. Current research focuses on adapting these black-box models to downstream tasks using gradient-free prompt optimization, but this often involves an expensive process of searching task-specific prompts. Therefore, we are motivated to study black-box language …

abstract apis arxiv black boxes box classification computation cs.cl current explore few-shot finetuning inference language language models llms research resources scale tasks them training type