Matching Tasks to Objectives: Fine-Tuning and Prompt-Tuning Strategies for Encoder-Decoder Pre-trained Language Models

arXiv·medium signal

An empirical study comparing fine-tuning and prompt-tuning strategies across diverse pre-training objectives for encoder-decoder language models, mapping which task types favor which adaptation method. Offers practical guidance for teams choosing an adaptation strategy on a fixed compute budget rather than defaulting to full fine-tuning.