I am currently pursuing an M.S. degree in Computer Science at Northeastern University, focusing on Information Retrieval and Large Language Models.
My research interests span NLP, LLM, RAG. Currently, my work involves LLM-as-a-Judge, and instruction tuning for large language models.
I hold a B.S. degree in Northeastern University at Qinhuangdao, where I was supervised by Assistant Researcher Jingmei Guo. I am also engaged in research internships at NEUIR Lab under the guidance of Associate Professor Zhenghao Liu (from Tsinghua University), as well as at Qiyuan Lab and THUNLP, supervised by Yukun Yan (from Tsinghua University).
📝 Publications
* indicates equal contribution, and † indicates corresponding author.
Judge as A Judge: Improving the Evaluation of Retrieval-Augmented Generation through the Judge-Consistency of Large Language Models
Shuliang Liu$^{*}$, Xinze Li$^{*}$, Zhenghao Liu$^†$,Yukun Yan,Cheng Yang,Zheni Zeng,Zhiyuan Liu,Maosong Sun,Ge Yu 📃Paper | 📄PDF
- This paper introduces the Judge-Consistency (ConsJudge) method, which aims to enhance LLMs to generate more accurate evaluations for RAG models.