• search
    search
  • reviewers
    reviewers
  • feeds
    feeds
  • assignments
    assignments
  • settings
  • logout

Aligning Large Language Models with Human Preferences through Representation Engineering.

Wenhao LiuXiaohua WangMuling WuTianlong LiChangze LvZixuan LingJianhao ZhuCenyuan ZhangXiaoqing ZhengXuanjing Huang
Published in: CoRR (2023)
Keyphrases