Neat project! I would be interested in a paper about this.
I think the tricky part with this type of technology is that, this works if the training data was not curated. What I mean is, if someone trains an LLM to simply not include key events it will not be able to reply
In that case you can use either rag or fine-tuning. The entire premise of the Tiananmen Square argument is just Americans feeling inferior. I use Chinese models every day for work and my personal life, the model not knowing about this one historical event has had zero impact on me.
I think the tricky part with this type of technology is that, this works if the training data was not curated. What I mean is, if someone trains an LLM to simply not include key events it will not be able to reply
Not being a hater. This is neato!