Tongjun Shi

Tongjun Shi

Auto-generated profile, based on publicly available information

Tongjun Shi

Futu Holdings Limited, Shenzhen, China

Research Focus & Metrics

Representative Publications

View All Publications
12 April 2026
Verified
Conference Paper
Open access
SZSenlei Zhang
Senlei Zhang
TSTongjun Shi
Tongjun Shi
DSDandan Song
Dandan Song
LZLuan Zhang
Luan Zhang
SZShuhao Zhang
Shuhao Zhang
HJHai Jin
Hai Jin
Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by leveraging external knowledge, where retrieval accuracy directly affects generation quality. However, dense retrievers, commonly employed in RAG, suffer degraded performance in evolving corpora where new documents arrive continuously and distribution shifts accumulate over time. In such settings, continually updating retrievers is crucial, yet conventional retraining is computationally expensive and often impractical. To address this challenge, we propose FlowRAG, a lightweight and effective method for continual retriever adaptation in evolving corpora. FlowRAG augments the encoder with Layer-wise Prompt Embeddings and introduces a Cross-Layer Fusion mechanism to capture hierarchical semantic representations. In addition, a novel Generator-Guided Loss aligns retriever scores and intermediate representations with the LLM's generation likelihoods, encouraging retrieval decisions that are both semantically relevant and beneficial for generation. Experiments on datasets spanning four domains demonstrate that FlowRAG, which updates only about 0.64% of the total model parameters, consistently outperforms strong baselines in retrieval accuracy, generation quality, and robustness to forgetting in non-stationary settings.

12 April 2026
Verified
Conference Paper
Open access
CLChangwu Li
Changwu Li
TSTongjun Shi
Tongjun Shi
SZShuhao Zhang
Shuhao Zhang
Bin ChenBin Chen
Bin Chen
BHBingsheng He
Bingsheng He
HJHai Jin
Hai Jin