RelAD is a reconstruction-based framework for anomaly detection on relational data that combines conditional sparse-gated attribute reconstruction with dual-view multi-relational edge reconstruction and outperforms baselines on 6 constructed benchmarks.
Dynhd: Hallucination detection for diffusion large language models via denoising dynam- ics deviation learning.arXiv preprint arXiv:2603.16459
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
Infilling extraction on diffusion language models extracts up to three times more verbatim sequences than prefix methods and achieves higher recall on redacted emails than autoregressive models.
CAMERA is an ego-decoupled mixture-of-experts model with context-informed gating and one-class objectives for unsupervised fraud detection in text-attributed graphs facing semantic camouflage.
OSCAR reduces hallucinations in diffusion language models by localizing commitment uncertainty with cross-chain entropy on parallel trajectories and applying evidence-guided remasking.
FedCIGAR improves federated graph anomaly detection via normal-graph reconstruction, client node gating, and server sliding-window clustering, claiming better performance than prior methods under data heterogeneity.
citing papers explorer
-
Towards Anomaly Detection on Relational Data
RelAD is a reconstruction-based framework for anomaly detection on relational data that combines conditional sparse-gated attribute reconstruction with dual-view multi-relational edge reconstruction and outperforms baselines on 6 constructed benchmarks.
-
Extracting Training Data from Diffusion Language Models via Infilling
Infilling extraction on diffusion language models extracts up to three times more verbatim sequences than prefix methods and achieves higher recall on redacted emails than autoregressive models.
-
CAMERA: Adapting to Semantic Camouflage in Unsupervised Text-Attributed Graph Fraud Detection
CAMERA is an ego-decoupled mixture-of-experts model with context-informed gating and one-class objectives for unsupervised fraud detection in text-attributed graphs facing semantic camouflage.
-
OSCAR: Orchestrated Self-verification and Cross-path Refinement
OSCAR reduces hallucinations in diffusion language models by localizing commitment uncertainty with cross-chain entropy on parallel trajectories and applying evidence-guided remasking.
-
FedCIGAR: A Personalized Reconstruction Approach for Federated Graph-level Anomaly Detection
FedCIGAR improves federated graph anomaly detection via normal-graph reconstruction, client node gating, and server sliding-window clustering, claiming better performance than prior methods under data heterogeneity.