I received my B.E. degree from Qingdao University in June 2018. In the same year, I was admitted to study for a M.Sc. degree in Nanjing University under the supervision of Prof. Qing Gu (顾庆) and Assistant Professor Zhiwei Jiang (蒋智威). Currently, I am working with Prof. Qing Gu (顾庆) and Assistant Professor Zhiwei Jiang (蒋智威) for a Ph.D. degree.

From May 2022 to March 2023, I was a research intern at Tencent Cloud Xiaowei, where I worked under the mentorship of Qingyu Zhou (周青宇), Zhao Yan (闫昭), and Yunbo Cao (曹云波).

Main Research Interests

I have a broad interest in large language models (LLMs) and natural language processing (NLP). Currently, I am primarily focusing on the following aspects:

• Intervention and Editing Techniques for LLMs

• Test-time or training-free algorithm for LLMs

• Attack and Defense of LLMs, mainly including model extraction attacks and watermarking

Research Experience

• Sep. 2021 - Present
  Ph.D. Candidate, School of Computer Science, Nanjing University

• Sep. 2018 - Jun. 2021
  M.Sc., Department of Computer Science and Technology, Nanjing University

• May 2022 - March 2023
  Tencent Cloud Xiaowei, CSIG, Tencent

Selected Publications

2024

• Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs
  Yuchen Fu*, Zifeng Cheng*, Zhiwei Jiang, Zhonghui Wang, Yafeng Yin, Zhengliang Li, and Qing Gu
  arXiv: 2412.11556, 2024. (arXiv 2024)

• A Debiased Nearest Neighbors Framework for Multi-Label Text Classification
  Zifeng Cheng, Zhiwei Jiang, Yafeng Yin, Zhaoling Chen, Cong Wang, Shiping Ge, Qiguo Huang, and Qing Gu
  arXiv: 2408.03202, 2024. (arXiv 2024)

• Multi-Prompting Decoder Helps Better Language Understanding
  Zifeng Cheng*, Zhaoling Chen*, Zhiwei Jiang, Yafeng Yin, Shiping Ge, Yuliang Liu, and Qing Gu
  arXiv: 2406.06279, 2024. (arXiv 2024)

2023

• Unifying Token and Span Level Supervisions for Few-Shot Sequence Labeling
  Zifeng Cheng, Qingyu Zhou, Zhiwei Jiang, Xuemin Zhao, Yunbo Cao, and Qing Gu
  ACM Transactions on Information Systems, 2023. (TOIS 2023)

2022

• A Consistent Dual-MRC Framework for Emotion-Cause Pair Extraction
  Zifeng Cheng, Zhiwei Jiang, Yafeng Yin, Cong Wang, Shiping Ge, and Qing Gu
  ACM Transactions on Information Systems, 2022. (TOIS 2022)

• Learning to Classify Open Intent via Soft Labeling and Manifold Mixup
  Zifeng Cheng, Zhiwei Jiang, Yafeng Yin, Cong Wang, and Qing Gu
  IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2022. (TASLP 2022)

2021

• A Unified Target-Oriented Sequence-to-Sequence Model for Emotion-Cause Pair Extraction
  Zifeng Cheng, Zhiwei Jiang, Yafeng Yin, Na Li, and Qing Gu
  IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2021. (TASLP 2021)

2020

• A Symmetric Local Search Network for Emotion-Cause Pair Extraction
  Zifeng Cheng, Zhiwei Jiang, Yafeng Yin, Hua Yu, and Qing Gu
  In Proceedings of the 28th International Conference on Computational Linguistics, 2020. (COLING 2020)

Selected Awards and Honors

• The First Youth Talents Support Project - Doctoral Student Special Program, China Association for Science and Technology, 2024 (only 3,226 doctoral students in China)
• National Scholarship, China, 2024
• Yingcai Scholarship, Nanjing University, 2023
• Tencent Rhino-Bird Research Elite Program, 2022
• Huawei Scholarship, Nanjing University, 2022
• Yingcai Scholarship, Nanjing University, 2021
• YEEPAY Scholarship, Nanjing University, 2020
• Outstanding Graduate Student, Nanjing University, 2020

Professional Services

Program Committee Member (Reviewer):

• Conference: ACL Rolling Review(ARR), ICLR(2025), COLING(2024), EMNLP(2023), EMNLP(2022), COLING(2022), EMNLP(2021)

• Journal: TASLP

Correspondence

• Email: chengzf@smail.nju.edu.cn

• Office: Room 612, Computer Science Building, Xianlin Campus of Nanjing University