Tianlong Li

发表

Tailoring Personality Traits in Large Language Models via Unsupervisedly-Built Personalized Lexicons

Tianlong Li, Xiaoqing Zheng, Xuanjing Huang, 2023, ArXiv.

Open the Pandora's Box of LLMs: Jailbreaking LLMs through Representation Engineering

Tianlong Li, Xiaoqing Zheng, Xuanjing Huang, 2024, ArXiv.

SpikeBERT: A Language Spikformer Learned from BERT with Knowledge Distillation

Jianhan Xu, Tianlong Li, Xiaoqing Zheng, 2023, 2308.15122.

Aligning Large Language Models with Human Preferences through Representation Engineering

Tianlong Li, Xiaoqing Zheng, Xuanjing Huang, 2023, ACL.