PPFT enables text-free LLM inference by aligning client embeddings with server projection and LLM, then fine-tuning on noise-injected private embeddings to maintain near-baseline performance without exposing raw prompts.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Towards Privacy-Preserving Large Language Model: Text-free Inference Through Alignment and Adaptation
PPFT enables text-free LLM inference by aligning client embeddings with server projection and LLM, then fine-tuning on noise-injected private embeddings to maintain near-baseline performance without exposing raw prompts.