-
Notifications
You must be signed in to change notification settings - Fork 52
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
请问现在的master分支中为什么只有single-single的代码了 #22
Comments
你好,感谢对我们工作的关注。目前的代码可以支持single model情况下的single question/multi question的fuzz,传入的question可以是一个单个的str或者一个list。请参考 |
你好,请问为什么我在实验中parent的选择基本都是在0,1,2中呢? |
你好,请问你攻击对象模型是哪个?因为MCTSExplore算法虽然设计上对比MCTS和UCB更加注重explore,但仍然有可能会陷入局部最优。如果模型的鲁棒性较弱并且一开始对于parent 0,1,2进行选择并且获得较好结果,就有可能再次对0,1,2这三个种子进行选择,如果又能攻击成功,就会进一步加剧这种情况。如果模型鲁棒性较弱,可以在种子选择算法中改成RoundRobinSelectPolicy或者RandomSelectPolicy确保所有的种子都是平等选择的,这样会稍微牺牲一些performance,但是可以保证生成结果中parent的多样性 |
非常感谢您的解答!我的攻击目标是qwen-7b-chat,他的鲁棒性确实一般,在llm-attacks中的表现和vicuna差不多 |
如题
The text was updated successfully, but these errors were encountered: