AI RESEARCH
From Context to Skills: Can Language Models Learn from Context Skillfully?
arXiv CS.AI
•
ArXi:2604.27660v1 Announce Type: new Many real-world tasks require language models (LMs) to reason over complex contexts that exceed their parametric knowledge. This calls for context learning, where LMs directly learn relevant knowledge from the given context. An intuitive solution is inference-time skill augmentation: extracting the rules and procedures from context into natural-language skills.