4 papers
ZenGen: Social Mind for LLMs
ZenGen Team, Zing Team, Ao Xiang +57
As large language models move from isolated task solving toward long-term service in human environments, they require social intelligence: the ability to infer mental states, track…
Projecting Out the Malice: A Global Subspace Approach to LLM Detoxification
Zenghao Duan, Zhiyi Yin, Zhichao Shi +8
Large language models (LLMs) exhibit exceptional performance but pose inherent risks of generating toxic content, restricting their safe deployment. While traditional methods (e.g.…
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace
Zenghao Duan, Zhiyi Yin, Zhichao Shi +6
This paper investigates the underlying mechanisms of toxicity generation in Large Language Models (LLMs) and proposes an effective detoxification approach. Prior work typically con…
Related Knowledge Perturbation Matters: Rethinking Multiple Pieces of Knowledge Editing in Same-Subject
Zenghao Duan, Wenbin Duan, Zhiyi Yin +5
Knowledge editing has become a promising approach for efficiently and precisely updating knowledge embedded in large language models (LLMs). In this work, we focus on Same-Subject…