Multi-generation sampling from LLMs uncovers more jailbreak behaviors than single generations, with the largest gains from one to moderate sample counts and diminishing returns thereafter.
In: Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security, pp
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A modified Llama 3 model using fully homomorphic encryption achieves up to 98% text generation accuracy and 80 tokens per second at 237 ms latency on an i9 CPU.
citing papers explorer
-
An Empirical Study of Multi-Generation Sampling for Jailbreak Detection in Large Language Models
Multi-generation sampling from LLMs uncovers more jailbreak behaviors than single generations, with the largest gains from one to moderate sample counts and diminishing returns thereafter.
-
Fully Homomorphic Encryption on Llama 3 model for privacy preserving LLM inference
A modified Llama 3 model using fully homomorphic encryption achieves up to 98% text generation accuracy and 80 tokens per second at 237 ms latency on an i9 CPU.