This is especially problematic because of how easily (and unconsciously) one can bias LLMs with how the prompt is framed.
As an experiment, I recently asked an LLM to analyse the export of a text chat to uncover relationship dynamics.
Simply stating that I was one of the people in the chat would make the LLM turn the other person into the villain. None of that was visible if I framed the chat as only involving third party people.
As an experiment, I recently asked an LLM to analyse the export of a text chat to uncover relationship dynamics.
Simply stating that I was one of the people in the chat would make the LLM turn the other person into the villain. None of that was visible if I framed the chat as only involving third party people.