Publications

Manuscripts

• LIFEBench: Evaluating Length Instruction Following in Large Language Models
  Wei Zhang*, Zhenhong Zhou*, Junfeng Fang*, Rongwu Xu*, Kun Wang*, Yuanhe Zhang, Rui Wang, Ge Zhang, Xinfeng Li, Li Sun, Lingjuan Lyu, Yang Liu, Sen Su
  arXiv Preprint
  [Paper][Project Page][Code][HF]
• AI Awareness
  Xiaojian Li, Haoyuan Shi, Rongwu Xu†, Wei Xu
  arXiv Preprint
  [Paper][Project Page]
• Humanity's Last Exam
  Long Phan, Alice Gatti, Ziwen Han, Nathaniel Li, ... Rongwu Xu ..., Summer Yue, Alexandr Wang, Dan Hendrycks
  arXiv Preprint
  [Paper][Project Page]
  
• Rules Created by Symbolic Systems Cannot Constrain a Learning System
  Shih-Wai Lin, Rongwu Xu, Xiaojian Li, Wei Xu
  SSRN Preprint
  [Paper]
  
• DebateQA: Evaluating Question Answering on Debatable Knowledge
  Rongwu Xu*, Xuan Qi*, Zehan Qi, Wei Xu, Zhijiang Guo
  arXiv Preprint
  [Paper][Code]
  

Conferences & Journals

2025

• Nuclear Deployed: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agents
  Rongwu Xu*, Xiaojian Li*, Shuo Chen*, Wei Xu
  ACL 2025 Findings
  [Paper][Project Page][Code][X Post][Slides][AI Safety China]
• Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking?
  Chengda Lu, Xiaoyu Fan, Yu Huang, Rongwu Xu, Jijie Li, Wei Xu
  ACL 2025 Findings
  
• On the Role of Attention Heads in Large Language Model Safety
  Zhenhong Zhou, Haiyang Yu, Xinghua Zhang, Rongwu Xu, Fei Huang, Kun Wang, Yang Liu, Junfeng Fang, Yongbin Li
  ICLR 2025 Oral
  [Paper][Code]
  

2024

• MR-BEN: A Comprehensive Meta-Reasoning Benchmark for Large Language Models
  Zhongshen Zeng, Yinhong Liu, Yingjia Wan, Jingyao Li, Pengguang Chen, Jianbo Dai, Yuxuan Yao, Rongwu Xu, Zehan Qi, Wanru Zhao, Linling Shen, Jianqiao Lu, Haochen Tan, Yukang Chen, Hao Zhang, Zhan Shi, Bailin Wang, Zhijiang Guo, Jiaya Jia
  NeurIPS 2024
  [Paper][Project Page][Code]
  
• Knowledge Conflicts for LLMs: A Survey
  Rongwu Xu*, Zehan Qi*, Zhijiang Guo, Cunxiang Wang, Hongru Wang, Yue Zhang, Wei Xu
  EMNLP 2024
  [Paper][Code][机器之心][Talk (Chinese)][Slides][Poster][X Post]
  
• Walking in Others' Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias
  Rongwu Xu, Zi'an Zhou, Tianwei Zhang, Zehan Qi, Su Yao, Ke Xu, Wei Xu, Han Qiu
  EMNLP 2024
  [Paper][Poster]
  
• Course-Correction: Safety Alignment Using Synthetic Preferences
  Rongwu Xu*, Yishuo Cai*, Zhenhong Zhou, Renjie Gu, Haiqin Wang, Yan Liu, Tianwei Zhang, Wei Xu, Han Qiu
  EMNLP 2024
  [Paper][Code][Poster][X Post]
  
• $LONG^{2}RAG$: Evaluating Long-Context & Long-Form Retrieval-Augmented Generation with Key Point Recall
  Zehan Qi*, Rongwu Xu*, Zhijiang Guo, Cunxiang Wang, Hao Zhang, Wei Xu
  EMNLP 2024 Findings
  [Paper]
  
• How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States
  Zhenhong Zhou, Haiyang Yu, Xinghua Zhang, Rongwu Xu, Fei Huang, Yongbin Li
  EMNLP 2024 Findings
  [Paper][Code][Poster]
  
• Sing it, Narrate it: Quality Musical Lyrics Translation
  Zhuorui Ye, Jinhan Li, Rongwu Xu
  EMNLP 2024 Findings
  [Paper]
  
• The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation
  Rongwu Xu, Brian S. Lin, Shujian Yang, Tianqi Zhang, Weiyan Shi, Tianwei Zhang, Zhixuan Fang, Wei Xu, Han Qiu
  ACL 2024 Oral
  🏆 Outstanding Paper Award [Certificate]
  [Paper][Project Page][Code][机器之心][Video][Poster][Slides]
  
• Preemptive Answer ``Attacks'' on Chain-of-Thought Reasoning
  Rongwu Xu*, Zehan Qi*, Wei Xu
  ACL 2024 Findings
  [Paper][Code][Poster]
  
• Exploring Chinese Humor Generation: A Study on Two-Part Allegorical Sayings
  Rongwu Xu
  IJCNN 2024
  [Paper]
  
• Tempo: Confidentiality Preservation in Cloud-Based Neural Network Training
  Rongwu Xu and Zhixuan Fang
  IJCNN 2024
  [Paper]
  
• LSync: A Universal Timeline-synchronizing Solution for Live Streaming
  Fan Dang*, Yifan Xu*, Rongwu Xu, Xinlei Chen, Yunhao Liu
  IEEE/ACM Trans. on Networking
  [Paper]
  

2023

• MISO: Legacy-compatible Privacy-preserving Single Sign-on using Trusted Execution Environments
  Rongwu Xu, Sen Yang, Fan Zhang, Zhixuan Fang
  EuroS&P 2023
  [Paper][Project Page][Slides]
  

2022

• LSync: A Universal Event-synchronizing Solution for Live Streaming
  Yifan Xu, Fan Dang, Rongwu Xu, Xinlei Chen, Yunhao Liu
  INFOCOM 2022
  [Paper]
  
• LifeRec: A Mobile App for Lifelog Recording and Ubiquitous Recommendation
  Jiayu Li, Hantian Zhang*, Zhiyu He*, Rongwu Xu*, Pingfei Wu*, Min Zhang, Yiqun Liu, Shaoping Ma
  CHIIR 2022
  [Paper][Code]
  

Reports

• The Singapore Consensus on Global AI Safety Research Priorities: Building a Trustworthy, Reliable and Secure AI Ecosystem
  Dawn Song, Lan Xue, Luke Ong, Max Tegmark, Stuart Russell, Tegan Maharaj, Ya-Qin Zhang, Yoshua Bengio, ... Rongwu Xu and others
  SCAI 2025
  [Paper][Project Page]

(* equal contribution, † corresponding author)