Yiquan Wu

Yiquan Wu

Auto-generated profile, based on publicly available information

Yiquan Wu

Zhejiang University, Hangzhou, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 July 2023
Verified
Conference Paper
Open access
YLYifei Liu
Yifei Liu
YWYiquan Wu
Yiquan Wu
YZYating Zhang
Yating Zhang
CSChanglong Sun
Changlong Sun
WLWeiming Lu
Weiming Lu
KKKun Kuang
Kun Kuang

8 May 2025
Verified
Conference Paper
Open access
RYRujing Yao
Rujing Yao
YWYiquan Wu
Yiquan Wu
TZTong Zhang
Tong Zhang
XZXuhui Zhang
Xuhui Zhang
YHYuting Huang
Yuting Huang
XLXiaozhong Liu
Xiaozhong Liu

24 August 2024
Verified
Conference Paper
Open access
YWYiquan Wu
Yiquan Wu
BTBo Tang
Bo Tang
CXChenyang Xi
Chenyang Xi
YYYu Yu
Yu Yu
PWPengyu Wang
Pengyu Wang
MYMingchuan Yang
Mingchuan Yang
Commentary provides readers with a deep understanding of events by presenting diverse arguments and evidence. However, creating commentary is a time-consuming task, even for skilled commentators. Large language models (LLMs) have simplified the process of natural language generation, but their direct application in commentary creation still faces challenges due to unique task requirements. These requirements can be categorized into two levels: 1) fundamental requirements, which include creating well-structured and logically consistent narratives, and 2) advanced requirements, which involve generating quality arguments and providing convincing evidence. In this paper, we introduce Xinyu, an efficient LLM-based system designed to assist commentators in generating Chinese commentaries. To meet the fundamental requirements, we deconstruct the generation process into sequential steps, proposing targeted strategies and supervised fine-tuning (SFT) for each step. To address the advanced requirements, we present an argument ranking model for arguments and establish a comprehensive evidence database that includes up-to-date events and classic books, thereby strengthening the substantiation of the evidence with retrieval augmented generation (RAG) technology. To evaluate the generated commentaries more fairly, corresponding to the two-level requirements, we introduce a comprehensive evaluation metric that considers five distinct perspectives in commentary generation. Our experiments confirm the effectiveness of our proposed system. We also observe a significant increase in the efficiency of commentators in real-world scenarios, with the average time spent on creating a commentary dropping from 4 hours to 20 minutes. Importantly, such an increase in efficiency does not compromise the quality of the commentaries.

16 June 2025
Verified
Conference Paper
Open access
TZTong Zhang
Tong Zhang
YWYiquan Wu
Yiquan Wu
RYRujing Yao
Rujing Yao
QZQianyu Zhang
Qianyu Zhang
CSChanglong Sun
Changlong Sun
XLXiaozhong Liu
Xiaozhong Liu


29 July 2025 in Computer Law & Security Review
Verified
Journal Article
Closed access
BWBin Wei
Bin Wei
YYYaoyao Yu
Yaoyao Yu
JZJiawen Zhang
Jiawen Zhang
YWYiquan Wu
Yiquan Wu