ReGA uses safety-critical representations to guide abstraction in model-based analysis, enabling scalable detection of harmful LLM inputs with reported AUROC of 0.975 at prompt level.
Weighted automata extraction and ex- planation of recurrent neural networks for natural language tasks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ReGA: Model-Based Safeguard for LLMs via Representation-Guided Abstraction
ReGA uses safety-critical representations to guide abstraction in model-based analysis, enabling scalable detection of harmful LLM inputs with reported AUROC of 0.975 at prompt level.