← Search

Haibing Jin

2 accepted papers

2026

Pisces: Cryptography-based Private Retrieval-Augmented Generation with Dual-Path Retrieval

ICLR 2026poster

Retrieval-augmented generation (RAG) enhances the response quality of large language models (LLMs) when handling domain-specific tasks, yet raises significant privacy concerns. This is because both the user query and documents within the knowledge base often contain sensitive or confidential informa…

Cited by 0Source ↗code ↗Scholar ↗
2023

FedGS: Federated Graph-Based Sampling with Arbitrary Client Availability

AAAI 2023technical

While federated learning has shown strong results in opti- mizing a machine learning model without direct access to the original data, its performance may be hindered by in- termittent client availability which slows down the conver- gence and biases the final learned model. There are significant ch…