AI RESEARCH
Token-Efficient Change Detection in LLM APIs
arXiv CS.LG
•
ArXi:2602.11083v2 Announce Type: replace Remote change detection in LLMs is a difficult problem. Existing methods are either too expensive for deployment at scale, or require initial white-box access to model weights or grey-box access to log probabilities. We aim to achieve both low cost and strict black-box operation, observing only output tokens. Our approach hinges on specific inputs we call Border Inputs, for which there exists than one output top token.