Tianlong Yu
3 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces TrojanMerge, a framework demonstrating that model merging can be exploited to systematically compromise the safety alignment of multiple individually safe LLMs.
The paper proposes UNSEEN, a cross-stack defense system combining AR access control, LLM unlearning, and agent guardrails to mitigate sophisticated AR-LLM social engineering attacks.
The paper proposes a framework, QMFOL, for generating monadic first-order logic reasoning tasks with controllable complexity to evaluate large language models.
Papers
QMFOL: Benchmarking Large Language Model Reasoning via Quantifiable Monadic First-Order Logic Test Case Generation
Xinyi Zheng, Ling Shi, Tianlong Yu, Yongxin Zhao +2 more
The paper proposes a framework, QMFOL, for generating monadic first-order logic reasoning tasks with controllable complexity to evaluate large language models.