How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs

1 code implementation • 12 Jan 2024 • Yi Zeng, Hongpeng Lin, Jingwen Zhang, Diyi Yang, Ruoxi Jia, Weiyan Shi

This paper introduces a new perspective to jailbreak LLMs as human-like communicators, to explore this overlooked intersection between everyday language interaction and AI safety.

TikTalk: A Video-Based Dialogue Dataset for Multi-Modal Chitchat in Real World

1 code implementation • 14 Jan 2023 • Hongpeng Lin, Ludan Ruan, Wenke Xia, Peiyu Liu, Jingyuan Wen, Yixin Xu, Di Hu, Ruihua Song, Wayne Xin Zhao, Qin Jin, Zhiwu Lu

Experimental results indicate that the models incorporating large language models (LLM) can generate more diverse responses, while the model utilizing knowledge graphs to introduce external knowledge performs the best overall.

Knowledge Graphs