Zhilin Wang

About Me

Hello, I’m Zhilin Wang, an undergraduate student at Jilin University. Previously, I studied as a visiting student under the supervision of Yue Zhang at WestlakeNLP. I am currently an incoming PhD student, under the supervision of Yu Cheng, at the University of Science and Technology of China (USTC) and the Shanghai AI Lab.

Projects

PASTED: A paraphrased text span detection method, which recognizes the distinct writing patterns of AI-paraphrased spans compared to the surrounding text. Repo
DeTect: AI-generated text detection system built on a comprehensive dataset containing 447,674 human-written and machine-generated texts from various sources. Repo
Computer-Graphics-Lab-For-JLU: Developed to update Jilin University’s Computer Graphics course experiments, based on games101 and including a complete implementation of a rendering pipeline. Repo

Publications

ACL

Unveiling Attractor Cycles in Large Language Models: A Dynamical Systems View of Successive Paraphrasing

Zhilin Wang*, Yafu Li*, Jianhao Yan, Yu Cheng, Yue Zhang

PDF Code

ACL findings

SEE: Continual Fine-tuning with Sequential Ensemble of Experts

Zhilin Wang, Yafu Li, Xiaoye Qu, Yu Cheng

PDF Code

Arxiv

From Drafts to Answers: Unlocking LLM Potential via Aggregation Fine-Tuning

Yafu Li*, Zhilin Wang*, Tingchen Fu, Ganqu Cui, Sen Yang, Yu Cheng

PDF Code

ACL findings

Spotting AI’s Touch: Identifying LLM-Paraphrased Spans in Text

Yafu Li*, Zhilin Wang*, Leyang Cui, Wei Bi, Shuming Shi, Yue Zhang

In Proceedings of the 62st Annual Meeting of the Association for Computational Linguistics, 2024.

PDF Code

ACL

Lost in Literalism: How Supervised Training Shapes Translationese in LLMs

Yafu Li, Ronghao Zhang, Zhilin Wang, Huajian Zhang, Leyang Cui, Yongjing Yin, Tong Xiao, Yue Zhang

PDF

ACL

DETect: Deepfake Text Detection in the Wild

Yafu Li, Qintong Li, Leyang Cui, Wei Bi, Zhilin Wang, Longyue Wang, Linyi Yang, Shuming Shi, Yue Zhang

In Proceedings of the 62st Annual Meeting of the Association for Computational Linguistics, 2024.

PDF Code BibTex

ACL

Just Like a Human Would, Direct Access to Sarcasm Augmented with Potential Result and Reaction

Changrong Min, Ximing Li, Liang Yang, Zhilin Wang, Bo Xu, and Hongfei Lin

In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, 2023.

PDF BibTex

Experience

Shanghai Ai Lab, 2024.9 ~ present
WestlakeNLP visiting student, 2023.7 ~ 2023.9 & 2024.6 ~ 2023.8
Jilin University, 2021.8 ~ present

Awards

Huawei ICT Competition: Global Grand Prize, 2023
Computer Games: First Prize, 2023
CCF BDCI: Third Prize, 2022
The First Prize Scholarship, 2022~2023 & 2023~2024

Service

Volunteer at NLPCC 2024