AI RESEARCH
Reconstruction of Personally Identifiable Information from Supervised Finetuned Models
arXiv CS.LG
•
ArXi:2605.12264v1 Announce Type: cross Supervised Finetuning (SFT) has become one of the primary methods for adapting a large language model (LLM) with extensive pre-trained knowledge to domain-specific, instruction-following tasks. SFT datasets, composed of instruction-response pairs, often include user-provided information that may contain sensitive data such as personally identifiable information (PII), raising privacy concerns. This paper studies the problem of PII reconstruction from SFT models for the first time.