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.
InFindings of the Association for Computational Linguistics: ACL 2025, pages 26196– 26220
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
A survey that introduces a unified training pipeline and taxonomizes split learning approaches for LLM fine-tuning across model, system, and privacy dimensions.
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.
-
A Survey on Split Learning for LLM Fine-Tuning: Models, Systems, and Privacy Optimizations
A survey that introduces a unified training pipeline and taxonomizes split learning approaches for LLM fine-tuning across model, system, and privacy dimensions.