Chenghao Zhang

Chenghao Zhang

he/his

My Name is Chenghao Zhang. I am currently a PhD student at the Gaoling School of Artificial Intelligence, Renmin University of China. My research interest is NLP+IR.

Publications

You can also find my articles on my Google Scholar profile.

Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation

Published in arXiv, 2024

DPA-RAG is a universal framework for aligning diverse preference knowledge within RAG systems, consisting of three main components: Preference Knowledge Construction, Reranker-LLM Alignment and LLM Self-Alignment.

Recommended citation: Yutao Zhu, Peitian Zhang, Chenghao Zhang, Yifei Chen, Binyu Xie, Zhicheng Dou, Zheng Liu, Ji-Rong Wen: INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuning. CoRR abs/2401.06532 (2024) http://snownation101.github.io/files/DPA.pdf

FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research

Published in arXiv, 2024

FlashRAG is a Python toolkit for the reproduction and development of Retrieval Augmented Generation (RAG) research. Our toolkit includes 32 pre-processed benchmark RAG datasets and 13 state-of-the-art RAG algorithms.

Recommended citation: Guanting Dong, Yutao Zhu, Chenghao Zhang, Zechen Wang, Zhicheng Dou, Ji-Rong Wen: Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation. CoRR abs/2406.18676 (2024) http://snownation101.github.io/files/FlashRAG.pdf