AI RESEARCH
Automated Instruction Revision (AIR): A Structured Comparison of Task Adaptation Strategies for LLM
arXiv CS.LG
•
ArXi:2604.09418v1 Announce Type: cross This paper studies Automated Instruction Revision (AIR), a rule-induction-based method for adapting large language models (LLMs) to downstream tasks using limited task-specific examples. We position AIR within the broader landscape of adaptation strategies, including prompt optimization, retrieval-based methods, and fine-tuning. We then compare these approaches across a diverse benchmark suite designed to stress different task requirements, such as knowledge injection, structured extraction, label remapping, and logical reasoning.