5 papers
SeSE: Black-Box Uncertainty Quantification for Large Language Models Based on Structural Information Theory
Xingtao Zhao, Hao Peng, Dingli Su +4
Reliable uncertainty quantification (UQ) is essential for deploying large language models (LLMs) in safety-critical scenarios, as it enables them to abstain from responding when un…
RoBCtrl: Attacking GNN-Based Social Bot Detectors via Reinforced Manipulation of Bots Control Interaction
Yingguang Yang, Xianghua Zeng, Qi Wu +5
Social networks have become a crucial source of real-time information for individuals. The influence of social bots within these platforms has garnered considerable attention from…
Certainly Bot Or Not? Trustworthy Social Bot Detection via Robust Multi-Modal Neural Processes
Qi Wu, Yingguang Yang, hao liu +4
Social bot detection is crucial for mitigating misinformation, online manipulation, and coordinated inauthentic behavior. While existing neural network-based detectors perform well…
SeBot: Structural Entropy Guided Multi-View Contrastive Learning for Social Bot Detection
Yingguang Yang, Qi Wu, Buyun He +4
Recent advancements in social bot detection have been driven by the adoption of Graph Neural Networks. The social graph, constructed from social network interactions, contains beni…
BotDGT: Dynamicity-aware Social Bot Detection with Dynamic Graph Transformers
Buyun He, Yingguang Yang, Qi Wu +6
Detecting social bots has evolved into a pivotal yet intricate task, aimed at combating the dissemination of misinformation and preserving the authenticity of online interactions.…