Using LLama2 to find links in mental disorders and ideological fixation

[saternius]

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...

[NoZebra120vClip]

Don't worry, it will use very scientific biometrics. It will do a close scientific scan of the subject's head and skull, and by scientifically analyzing the contours, proportions, and qualities of the skull with scientifically established science, the AI will render a completely logical and scientific decision that has been scientifically proven for hundreds of years.

[saternius]

I could see how this comes off as linguistic phrenology. The point is not for this to be used diagnostically, but instead to analyze trends with the labels we use in language.