Fengqing Jiang

34 papers A* 6A 2C 1Journal 20Unranked 5

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	BadScientist: Can a Research Agent Write Convincing but Unsound Papers that Fool LLM Reviewers? CoRR Fengqing Jiang, Yichen Feng, Yuetai Li, Luyao Niu, Basel Alomair, Radha Poovendran
2025	A*	`conf`	ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates. AAAI Fengqing Jiang, Zhangchen Xu, Luyao Niu, Bill Yuchen Lin, Radha Poovendran
2025	A*	`conf`	Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. ICLR Zhangchen Xu, Fengqing Jiang, Luyao Niu, Yuntian Deng, Radha Poovendran, Yejin Choi, Bill Yuchen Lin
2025	J	`jnl`	SOSBENCH: Benchmarking Safety Alignment on Scientific Knowledge. CoRR Fengqing Jiang, Fengbo Ma, Zhangchen Xu, Yuetai Li, Bhaskar Ramasubramanian, Luyao Niu, Bo Li, Xianyan Chen, Zhen Xiang, Radha Poovendran
2025	—	`conf`	SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities. ACL (Findings) Fengqing Jiang, Zhangchen Xu, Yuetai Li, Luyao Niu, Zhen Xiang, Bo Li, Bill Yuchen Lin, Radha Poovendran
2025	J	`jnl`	SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities. CoRR Fengqing Jiang, Zhangchen Xu, Yuetai Li, Luyao Niu, Zhen Xiang, Bo Li, Bill Yuchen Lin, Radha Poovendran
2025	—	`conf`	Small Models Struggle to Learn from Strong Reasoners. ACL (Findings) Yuetai Li, Xiang Yue, Zhangchen Xu, Fengqing Jiang, Luyao Niu, Bill Yuchen Lin, Bhaskar Ramasubramanian, Radha Poovendran
2025	J	`jnl`	Small Models Struggle to Learn from Strong Reasoners. CoRR Yuetai Li, Xiang Yue, Zhangchen Xu, Fengqing Jiang, Luyao Niu, Bill Yuchen Lin, Bhaskar Ramasubramanian, Radha Poovendran
2025	—	`conf`	Stronger Models are Not Always Stronger Teachers for Instruction Tuning. NAACL (Long Papers) Zhangchen Xu, Fengqing Jiang, Luyao Niu, Bill Yuchen Lin, Radha Poovendran
2025	J	`jnl`	Temporal Sampling for Forgotten Reasoning in LLMs. CoRR Yuetai Li, Zhangchen Xu, Fengqing Jiang, Bhaskar Ramasubramanian, Luyao Niu, Bill Yuchen Lin, Xiang Yue, Radha Poovendran
2025	J	`jnl`	TinyV: Reducing False Negatives in Verification Improves RL for LLM Reasoning. CoRR Zhangchen Xu, Yuetai Li, Fengqing Jiang, Bhaskar Ramasubramanian, Luyao Niu, Bill Yuchen Lin, Radha Poovendran
2025	J	`jnl`	VisualSphinx: Large-Scale Synthetic Vision Logic Puzzles for RL. CoRR Yichen Feng, Zhangchen Xu, Fengqing Jiang, Yuetai Li, Bhaskar Ramasubramanian, Luyao Niu, Bill Yuchen Lin, Radha Poovendran
2024	A*	`conf`	ACE: A Model Poisoning Attack on Contribution Evaluation Methods in Federated Learning. USENIX Security Symposium Zhangchen Xu, Fengqing Jiang, Luyao Niu, Jinyuan Jia, Bo Li, Radha Poovendran
2024	J	`jnl`	ACE: A Model Poisoning Attack on Contribution Evaluation Methods in Federated Learning. CoRR Zhangchen Xu, Fengqing Jiang, Luyao Niu, Jinyuan Jia, Bo Li, Radha Poovendran
2024	—	`conf`	ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs. ACL (1) Fengqing Jiang, Zhangchen Xu, Luyao Niu, Zhen Xiang, Bhaskar Ramasubramanian, Bo Li, Radha Poovendran
2024	J	`jnl`	ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs. CoRR Fengqing Jiang, Zhangchen Xu, Luyao Niu, Zhen Xiang, Bhaskar Ramasubramanian, Bo Li, Radha Poovendran
2024	A*	`conf`	BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models. ICLR Zhen Xiang, Fengqing Jiang, Zidi Xiong, Bhaskar Ramasubramanian, Radha Poovendran, Bo Li
2024	J	`jnl`	BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models. CoRR Zhen Xiang, Fengqing Jiang, Zidi Xiong, Bhaskar Ramasubramanian, Radha Poovendran, Bo Li
2024	J	`jnl`	Brave: Byzantine-Resilient and Privacy-Preserving Peer-to-Peer Federated Learning. CoRR Zhangchen Xu, Fengqing Jiang, Luyao Niu, Jinyuan Jia, Radha Poovendran
2024	J	`jnl`	ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates. CoRR Fengqing Jiang, Zhangchen Xu, Luyao Niu, Bill Yuchen Lin, Radha Poovendran
2024	A*	`conf`	CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models. EMNLP Yuetai Li, Zhangchen Xu, Fengqing Jiang, Luyao Niu, Dinuka Sahabandu, Bhaskar Ramasubramanian, Radha Poovendran
2024	J	`jnl`	CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models. CoRR Yuetai Li, Zhangchen Xu, Fengqing Jiang, Luyao Niu, Dinuka Sahabandu, Bhaskar Ramasubramanian, Radha Poovendran
2024	J	`jnl`	Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. CoRR Zhangchen Xu, Fengqing Jiang, Luyao Niu, Yuntian Deng, Radha Poovendran, Yejin Choi, Bill Yuchen Lin
2024	A	`conf`	POSTER: Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications. AsiaCCS Fengqing Jiang, Zhangchen Xu, Luyao Niu, Boxin Wang, Jinyuan Jia, Bo Li, Radha Poovendran
2024	A	`conf`	Poster: Brave: Byzantine-Resilient and Privacy-Preserving Peer-to-Peer Federated Learning. AsiaCCS Zhangchen Xu, Fengqing Jiang, Luyao Niu, Jinyuan Jia, Radha Poovendran
2024	—	`conf`	SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding. ACL (1) Zhangchen Xu, Fengqing Jiang, Luyao Niu, Jinyuan Jia, Bill Yuchen Lin, Radha Poovendran
2024	J	`jnl`	SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding. CoRR Zhangchen Xu, Fengqing Jiang, Luyao Niu, Jinyuan Jia, Bill Yuchen Lin, Radha Poovendran
2024	J	`jnl`	Stronger Models are NOT Stronger Teachers for Instruction Tuning. CoRR Zhangchen Xu, Fengqing Jiang, Luyao Niu, Bill Yuchen Lin, Radha Poovendran
2023	J	`jnl`	Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications. CoRR Fengqing Jiang, Zhangchen Xu, Luyao Niu, Boxin Wang, Jinyuan Jia, Bo Li, Radha Poovendran
2023	J	`jnl`	MDTD: A Multi Domain Trojan Detector for Deep Neural Networks. CoRR Arezoo Rajabi, Surudhi Asokraj, Fengqing Jiang, Luyao Niu, Bhaskar Ramasubramanian, James A. Ritcey, Radha Poovendran
2023	A*	`conf`	MDTD: A Multi-Domain Trojan Detector for Deep Neural Networks. CCS Arezoo Rajabi, Surudhi Asokraj, Fengqing Jiang, Luyao Niu, Bhaskar Ramasubramanian, James A. Ritcey, Radha Poovendran
2021	J	`jnl`	A Chinese Multi-type Complex Questions Answering Dataset over Wikidata. CoRR Jianyun Zou, Min Yang, Lichao Zhang, Yechen Xu, Qifan Pan, Fengqing Jiang, Ran Qin, Shushu Wang, Yifan He, Songfang Huang, Zhou Zhao
2021	J	`jnl`	An Action Recognition Algorithm for Sprinters Using Machine Learning. Mob. Inf. Syst. Fengqing Jiang, Xiao Chen
2021	C	`conf`	Towards Refinement of Unbounded Parallelism in ASMs Using Concurrency and Reflection. ABZ Fengqing Jiang, Neng Xiong, Xinyu Lian, Senén González, Klaus-Dieter Schewe