3 papers
cs.CL2024
Dishonesty in Helpful and Harmless Alignment
Youcheng Huang, Jingkun Tang, Duanyu Feng +4
People tell lies when seeking rewards. Large language models (LLMs) are aligned to human values with reinforcement learning where they get rewards if they satisfy human preference.…
cs.CL2024
Empirical Study on Updating Key-Value Memories in Transformer Feed-forward Layers
Zihan Qiu, Zeyu Huang, Youcheng Huang +1
The feed-forward networks (FFNs) in transformers are recognized as a group of key-value neural memories to restore abstract high-level knowledge. In this work, we conduct an empiri…
cs.CL2024
See the Unseen: Better Context-Consistent Knowledge-Editing by Noises
Youcheng Huang, Wenqiang Lei, Zheng Zhang +2
Knowledge-editing updates knowledge of large language models (LLMs) and contributes to the interpretability and application of LLMs. However, knowledge applying is context-consiste…