LLM cascade systems are vulnerable to a new adversarial attack that simultaneously degrades accuracy and destroys the intended cost savings by targeting both the lightweight models and the escalation decision mechanism.
Automix: Automati- cally mixing language models.Advances in Neu- ral Information Processing Systems, 37:131000– 131034
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
When Efficiency Backfires: Cascading LLMs Trigger Cascade Failure under Adversarial Attack
LLM cascade systems are vulnerable to a new adversarial attack that simultaneously degrades accuracy and destroys the intended cost savings by targeting both the lightweight models and the escalation decision mechanism.