13 citations · 14 across the 2 of their papers we have counts for
2 papers
cs.CL2023★ 13 cited
Detecting Language Model Attacks with Perplexity
Gabriel Alon, Michael Kamfonas
A novel hack involving Large Language Models (LLMs) has emerged, exploiting adversarial suffixes to deceive models into generating perilous responses. Such jailbreaks can trick LLM…
cs.CL2022★ 1 cited
What Can Secondary Predictions Tell Us? An Exploration on Question-Answering with SQuAD-v2.0
Michael Kamfonas, Gabriel Alon
Performance in natural language processing, and specifically for the question-answer task, is typically measured by comparing a modelś most confident (primary) prediction to golden…