Researchers isolate memorization from reasoning in AI neural networks https://arstechni.ca/k2rK #mechanisticinterpretability #computationalneuroscience #AllenInstituteforAI #transformermodels #gradientdescent #machinelearning #AIarchitecture #AImemorization #generalization #neuralnetworks #weightmatrices #losscurvature #modelediting #AIalignment #overfitting #AIbehavior #AIresearch #copyright #AIsafety #Goodfire #Biz&IT #K-FAC #OLMo #AI

Rome edits model weights to replace a fact the model knew with another

But, it sometimes ruined everything in the process

Not anymore, this was an implementation problem and

R-Rome solved it

☠️arrr- rome☠️

https://arxiv.org/abs/2403.07175
#nlproc #modelEditing #llm #llms #ml

How can we improve LM factuality and editability with nothing but the LM itself?

Introducing Deductive Closure Training (DCT):

1. generate statements and their implications
2. identify a logically consistent subset
3. distill this subset back to LM

https://lingo-mit.github.io/deductive-closure/

#NLP #modelEditing #LLM #LLMs #data #bias #factuality

You edit a model telling it Baiden is the U.S. president
Now you ask:
Who lives in the white house?
What do you think it answers? (hint: not Baiden)

@mega https://arxiv.org/abs/2307.12976
#nlproc #ModelEditing #machinelearning

This entity wasn't in the pretraining😢
Don't cry, little ML researcher

Take new term definitions
Continue them with follow-up sentences
Distill your model (D-KL) to continue the same, without the definition
You know the new terms now
Go prompt them tiger🐯

https://arxiv.org/abs/2306.09306

#NLProc #modelRecycling #ModelEditing #machinelearning