LVE Repository

bias

responsibility/bias/hiring_code

openai/gpt-4 1 Instances

responsibility/bias/hiring_code

openai/gpt-3.5-turbo 3 Instances

responsibility/bias/political_bias

mistralai/mistral-7b-instruct-v0.1 4 Instances

responsibility/bias/political_bias

openai/gpt-4 5 Instances

responsibility/bias/political_bias

openai/gpt-3.5-turbo 6 Instances

responsibility/bias/visual_hiring_bias

openai/gpt-4-vision-preview 9 Instances copyright

responsibility/copyright/articles/nytimes_paywall

openai/gpt-3.5-turbo 2 Instances

responsibility/copyright/songs/translation

openai/gpt-4 2 Instances dual_use

responsibility/dual_use/biology/jailbreak_influenza_1918_synthesis

openai/gpt-4 1 Instances

responsibility/dual_use/speech_prompt

openai/gpt-3.5-turbo 3 Instances harm

responsibility/harm/praising_villains

meta/llama-2-7b-chat 3 Instances

responsibility/harm/praising_villains

mistralai/mistral-7b-instruct-v0.1 4 Instances

responsibility/harm/praising_villains

openai/gpt-3.5-turbo 3 Instances

responsibility/harm/praising_villains

openai/gpt-4 2 Instances toxicity

responsibility/toxicity/appearance_comment

openai/gpt-4-vision-preview 5 Instances

responsibility/toxicity/chatgpt_offensive_comment

mistralai/mistral-7b-instruct-v0.1 5 Instances

responsibility/toxicity/chatgpt_offensive_comment

openai/gpt-4 6 Instances

responsibility/toxicity/chatgpt_offensive_comment

openai/gpt-3.5-turbo 4 Instances

responsibility/toxicity/insult_in_style

openai/gpt-3.5-turbo 4 Instances