SAEL combines LLM predictions, LLM-generated explanations, and code features via an adaptive mixture-of-experts gate and reports state-of-the-art F1 on four smart contract vulnerability benchmarks.
Dccgraph: Detecting criminal communities with augmented criminal network construction and graph neural network,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
SAEL: Leveraging Large Language Models with Adaptive Mixture-of-Experts for Smart Contract Vulnerability Detection
SAEL combines LLM predictions, LLM-generated explanations, and code features via an adaptive mixture-of-experts gate and reports state-of-the-art F1 on four smart contract vulnerability benchmarks.