I ran the 10groups question set (https://10groups.github.io) through Llama-2-70b-hf model to get a prediction on how likely the statement would correlate with the mental disorder on the top left. From this we were able to get a fixation score. Visit our git repo for details on the code and prompt that was used to generate this: https://github.com/saternius/LLMCompass/tree/master/llama2
I'm trying to find people who are interested in research like this. If you are, join this discord: https://discord.com/channels/1138851567861256333/11388515678...