Language models confuse roles based on how text sounds rather than its true source, enabling measurable prompt injection attacks via role probes that predict success rates.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Prompt Injection as Role Confusion
Language models confuse roles based on how text sounds rather than its true source, enabling measurable prompt injection attacks via role probes that predict success rates.