LM-Debugger builds upon our findings from this work https://t.co/fnEBgFe4b8
— Mor Geva (@megamor2) April 27, 2022
to provide three core capabilities for single-prediction debugging and model analysis 2/8 pic.twitter.com/Boer9BVEJD
(2) It also lets the user intervene in the prediction process by changing the weights of FFN updates of her choice, e.g. increasing (decreasing) an update that promotes music-related (teaching-related) tokens 4/8
— Mor Geva (@megamor2) April 27, 2022
Check out a demonstration of LM-Debugger here:https://t.co/nm6G4jrZCN
— Mor Geva (@megamor2) April 27, 2022
And try it out for yourself with our two demos:
GPT2 Medium: https://t.co/supnwK26CU
GPT2 Large: https://t.co/mYyZxKsm1n
6/8
Be sure to check out the video. It's very cool. Pay close attention, though. If you've never worked with such systems – I haven't – you may be puzzled on first viewing. It made more sense to me the second time around.
What I'm wondering is if something like this could be used to "bootstrap" a symbolic component into a neural net. I'm thinking of some posts where I discuss Vygotsky's account of language acquisition: Vygotsky Tutorial (for Connected Courses) and this one, Dual-system mentation in humans and machines [updated]. The second one involves a hybrid AI system with symbolic and neural net components.
