With the growing complexity of online information, trustworthy fake news detection has become increasingly critical. Although Large Language Models (LLMs) exhibit a strong ability to leverage factual evidence for verification, they remain highly vulnerable to unreliable, noisy, or scarce evidence, undermining robustnes...
Yu-Jing Wang, Xiao-Bao Wang, Yi-Qi Dong et al.· Proceedings of the Thirty-Fi...· 0 citations
The conversational recommendation system (CRS) breaks the limitations of traditional static methods, presenting a novel framework for personalized recommendations with real-time adaptability and dynamic interactions. Existing methods predominantly focus on the balance between ”exploration and exploitation (E&E)”, but t...
Di Jin, Run-Ze Li, Jia-Qi Cui et al.· ACM Transactions on Informat...· 0 citations
HGMRP extends single-relation prompts into a composite structure that includes both relation-specific and shared components, thereby enhancing expressive capability and significantly out-performs existing heterogeneous prompt methods, validating its effectiveness and superiority.
Fengyu Yan, Xiaobao Wang, Qian-Xi Tang et al.· 0 citations
The proposed Collateral Damage Constrained Graph Backdoor Attack (CDCA) combines neighborhood-aware target node selection with a self-constrained trigger generation strategy to suppress trigger-induced propagation by enforcing prediction consistency on clean K -hop neighboring nodes.
Di Jin, Ze-Chuan Zhang, Bing-Dao Feng et al.· Proceedings of the Thirty-Fi...· 0 citations
LoSplit is proposed, the first training-time defense framework in graph that leverages this early-stage loss drift to accurately split target nodes, and dynamically selects epochs with maximal loss divergence, clusters target nodes via Gaussian Mixture Models, and applies a Decoupling-Forgetting strategy to break the a...
Di Jin, Yuxiang Zhang, Bingdao Feng et al.· Neural Information Processin...· 4 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
