Text Generation
PEFT
Safetensors

PGPO

This repository contains the LoRA adapter introduced in PGPO: Prototype-Guided Progressive Obfuscation for Privacy-Preserving LLM-Enhanced Recommendation.

PGPO learns topology-aware, privacy-preserving prototype-word obfuscations while preserving inter-item semantic relations for LLM-enhanced recommendation. The adapter is trained with GRPO on top of Qwen3-4B-Base using TRL and Unsloth.

Code: https://github.com/Shengxiang-Lin/PGPO

Downloads last month
-
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for Shengxiang-Lin/PGPO

Adapter
(46)
this model

Paper for Shengxiang-Lin/PGPO