An automated two-stage rewriting framework, IntentPrompt, bypasses LLM content guardrails with 80-98% success by turning harmful asks into declarative outlines.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulation
An automated two-stage rewriting framework, IntentPrompt, bypasses LLM content guardrails with 80-98% success by turning harmful asks into declarative outlines.