Engorgio generates adversarial prompts that suppress <EOS> token probability and make auto-regressive LLMs generate near-maximum-length outputs, multiplying inference cost by 2-13x.
Rather, seek it
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
An Engorgio Prompt Makes Large Language Model Babble on
Engorgio generates adversarial prompts that suppress <EOS> token probability and make auto-regressive LLMs generate near-maximum-length outputs, multiplying inference cost by 2-13x.