Saved in:
Bibliographic Details
Main Authors: Han, Vernon Toh Yan, Bhardwaj, Rishabh, Poria, Soujanya
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.11654
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • We propose Ruby Teaming, a method that improves on Rainbow Teaming by including a memory cache as its third dimension. The memory dimension provides cues to the mutator to yield better-quality prompts, both in terms of attack success rate (ASR) and quality diversity. The prompt archive generated by Ruby Teaming has an ASR of 74%, which is 20% higher than the baseline. In terms of quality diversity, Ruby Teaming outperforms Rainbow Teaming by 6% and 3% on Shannon's Evenness Index (SEI) and Simpson's Diversity Index (SDI), respectively.