Hongpeng Lin
Welcome! I am a 3rd-year master student of Artificial Intelligence at Gaoling School of Artificial Intelligence, Renmin University of China. I’m advised by Prof. Ruihua Song, working on Natural Language Processing (NLP) and Multi-modal Dialogue. Prior to that, I completed my B.Eng. from School of Computer Science and Technology, Xidian University.
Email: hopelin@ruc.edu.cn / CV (Last updated in Aug. 2024)
Research Interests
My research interests are in Natural Language Processing and Multi-modal Understanding, with the hope of making machines perceive, understand, and express like humans.
Currently, my research focus is committed to adversarial robustness (jailbreaking LLMs and mitigations), long video understanding (natural language query localization), and creative multi-modal text generation (humor and association).
I am open for collaborations in research.
News
05/2024 Our paper on how to persuade LLMs to jailbreak them is accepted by ACL 2024 Main Conference!
01/2024 Check our new paper on how to persuade LLMs to jailbreak them with a success rate of 92%.
08/2023 Our paper “TikTalk” on multi-modal dialogue is accepted by ACM MM 2023!
Papers
How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs
Yi Zeng*, Hongpeng Lin* (lead authors), Jingwen Zhang, Diyi Yang, Ruoxi Jia*, Weiyan Shi* (co-supervise)
ACL 2024 Main Project Paper CodeTikTalk: A Video-Based Dialogue Dataset for Multi-Modal Chitchat in Real World
Hongpeng Lin*, Ludan Ruan*, Wenke Xia*, Peiyu Liu, Jingyuan Wen, Yixin Xu, Di Hu, Ruihua Song, Wayne Xin Zhao, Qin Jin, Zhiwu Lu
ACM MM 2023 (Oral) Project Paper Code
Service
- Conference reviewer: EMNLP, ACM MM, CVPR