It is possible, under some circumstances, to use contemporary large language models to detect how a subject feels about someone, even if they’re trying to hide it.
I have been working on an essay & research project to see where LLMs fail to understand meaning of clearly coherent sentences or ideas. I find your work fascinating in the opposite direction - where a model grasps the meaning better than humans. Also alarming!
I just published a pre-print about this. https://arxiv.org/abs/2608.18041
I have been working on an essay & research project to see where LLMs fail to understand meaning of clearly coherent sentences or ideas. I find your work fascinating in the opposite direction - where a model grasps the meaning better than humans. Also alarming!
Just published https://cindyholmes.substack.com/p/just-is-always-a-lie?r=bjbm&utm_medium=ios
Oh interesting! Tell me more about your project.