AI RESEARCH
Training-Free Test-Time Contrastive Learning for Large Language Models
arXiv CS.AI
•
ArXi:2604.13552v1 Announce Type: cross Large language models (LLMs) nstrate strong reasoning capabilities, but their performance often degrades under distribution shift. Existing test-time adaptation (TTA) methods rely on gradient-based updates that require white-box access and need substantial overhead, while