SIEVE: איחוד תשומת לב-ערך למודלים חזותיים-לשוניים

תקציר מקורי באנגליתarXiv:2610.01962v1 Announce Type: new Abstract: The ability of vision-language models (VLMs) to associate visual identities with biographical information creates a need for selective unlearning of personally identifiable information (PII) while preserving permitted knowledge about the same individual. This setting is challenging because both sensitive and retained information can share the same visual inputs and intermediate representations. We introduce SIEVE, a simple and effective framework for selective VLM unlearning. SIEVE directly regularizes attention-value representations while also controlling model outputs. SIEVE suppresses attention values for forget examples toward a constant zero, while preserving retain-example representations by matching them to a frozen reference model. Th