Improving LLM First-Token Predictions in Multiple-Choice Question Answering via Prefilling Attack

21 May 2025

Papers citing "Improving LLM First-Token Predictions in Multiple-Choice Question Answering via Prefilling Attack"

1 / 1 papers shown

Title
Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks Maksym Andriushchenko Francesco Croce Nicolas Flammarion AAML 210 222 0 02 Apr 2024