Toxic prompt perturbations reduce LLM factual accuracy on three benchmarks and selectively amplify perturbation-sensitive nodes in attribution graphs.
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
-
Toxic HallucinAItions: Perturbing Prompts and Tracing LLM Circuits
Toxic prompt perturbations reduce LLM factual accuracy on three benchmarks and selectively amplify perturbation-sensitive nodes in attribution graphs.