ALaRM: Align Language Models via Hierarchical Rewards Modeling F i n d i n g s - A C L

Yuhang Lai | Siyuan Wang | Shujun Liu | Xuanjing Huang | Zhongyu Wei |

Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs ACL

Siyuan Wang | Zhongyu Wei | Yejin Choi | Xiang Ren |

From LLMs to MLLMs: Exploring the Landscape of Multimodal Jailbreaking EMNLP

Siyuan Wang | Zhuohan Long | Zhihao Fan | Zhongyu Wei |

Symbolic Working Memory Enhances Language Models for Complex Rule Application EMNLP

Siyuan Wang | Zhongyu Wei | Yejin Choi | Xiang Ren |

In Search of the Long-Tail: Systematic Generation of Long-Tail Inferential Knowledge via Logical Rule Guided Search EMNLP

Huihan Li | Yuting Ning | Zeyi Liao | Siyuan Wang | Xiang Lorraine Li | Ximing Lu | Wenting Zhao | Faeze Brahman | Yejin Choi | Xiang Ren |