Xi Zhang

Full Professor@Beijing University of Posts and Telecommunications·中国·OpenReview

研究方向

LLM safety · jailbreak · hallucination · graph neural network · fake news detection · rumor detection · explainability · interpretibility · robustness · social network analysis · computational social science

4.0

Towards the Explainability of Temporal Graph Networks via Memory Backtracking

ICLR 2026Rejected

二作

2.5

REVOLUTIONIZING EVENT DETECTION: A NOVEL PROMPT-DRIVEN METHOD ENHANCED BY RETRIEVAL-AUGMENTED PARADIGM

ICLR 2026Rejected

一作

7.3

Robust Explanations of Graph Neural Networks via Graph Curvatures

NeurIPS 2025Poster

二作

6.4

One SPACE to Rule Them All: Jointly Mitigating Factuality and Faithfulness Hallucinations in LLMs

NeurIPS 2025Poster

通讯

4.0

Feint and Attack: Attention-Based Strategies for Jailbreaking and Protecting LLMs

合作者 (20)