raga-llm-hub

raga-llm-hub copied to clipboard

Good afternoon, I needed to carry out a test with the maliciousness_test function, but when I checked to invoke the function I received an error saying that the function is...

alantellecom

Safety evals, probably need more comprehensive and generic testing!

2

Great work! Regarding safety evals using inthewild_jailbreak_llms, not sure which roleplay dataset is this but it seems to be dedicated to jailbreak ChatGPT. Additionally, curious if there are any reasons...

Bhardwaj-Rishabh

GPT-4 and GPT-4o often prepend the json with ` ```json ` text. We now strip it during json loading

wwydmanski