3 papers
cs.CL2024
ConTrans: Weak-to-Strong Alignment Engineering via Concept Transplantation
Weilong Dong, Xinwei Wu, Renren Jin +2
Ensuring large language models (LLM) behave consistently with human goals, values, and intentions is crucial for their safety but yet computationally expensive. To reduce the compu…
cs.CL2024
IRCAN: Mitigating Knowledge Conflicts in LLM Generation via Identifying and Reweighting Context-Aware Neurons
Dan Shi, Renren Jin, Tianhao Shen +3
It is widely acknowledged that large language models (LLMs) encode a vast reservoir of knowledge after being trained on mass data. Recent studies disclose knowledge conflicts in LL…
cs.CL2024
Exploring Multilingual Concepts of Human Value in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages?
Shaoyang Xu, Weilong Dong, Zishan Guo +2
Prior research has revealed that certain abstract concepts are linearly represented as directions in the representation space of LLMs, predominantly centered around English. In thi…