The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse F i n d i n g s - A C L

Wanli Yang | Fei Sun | Xinyu Ma | Xun Liu | Dawei Yin | Xueqi Cheng |

When to Trust LLMs: Aligning Confidence with Response Quality F i n d i n g s - A C L

Shuchang Tao | Liuyi Yao | Hanxing Ding | Yuexiang Xie | Qi Cao | Fei Sun | Jinyang Gao | Huawei Shen | Bolin Ding |

Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts F i n d i n g s - A C L

Ganesh Jawahar | Haichuan Yang | Yunyang Xiong | Zechun Liu | Dilin Wang | Fei Sun | Meng Li | Aasish Pappu | Barlas Oguz | Muhammad Abdul-Mageed | Laks Lakshmanan | Raghuraman Krishnamoorthi | Vikas Chandra |

Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts? ACL

Hexiang Tan | Fei Sun | Wanli Yang | Yuanzhuo Wang | Qi Cao | Xueqi Cheng |

Pruning Foundation Models for High Accuracy without Retraining F i n d i n g s - E M N L P

Pu Zhao | Fei Sun | Xuan Shen | Pinrui Yu | Zhenglun Kong | Yanzhi Wang | Xue Lin |

The Fall of ROME: Understanding the Collapse of LLMs in Model Editing F i n d i n g s - E M N L P

Wanli Yang | Fei Sun | Jiajun Tan | Xinyu Ma | Du Su | Dawei Yin | Huawei Shen |