BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents ACL

Yifei Wang | Dizhan Xue | Shengjie Zhang | Shengsheng Qian |

Experiential Co-Learning of Software-Developing Agents ACL

Chen Qian | Yufan Dang | Jiahao Li | Wei Liu | Zihao Xie | YiFei Wang | Weize Chen | Cheng Yang | Xin Cong | Xiaoyin Che | Zhiyuan Liu | Maosong Sun |

Encourage or Inhibit Monosemanticity? Revisit Monosemanticity from a Feature Decorrelation Perspective EMNLP

Hanqi Yan | Yanzheng Xiang | Guangyi Chen | Yifei Wang | Lin Gui | Yulan He |

Unveiling Factual Recall Behaviors of Large Language Models through Knowledge Neurons EMNLP

Yifei Wang | Yuheng Chen | Wanting Wen | Yu Sheng | Linjing Li | Daniel Dajun Zeng |