MIT CSAIL News ·
Zheng Dai and David Gifford discuss removing training data to test its effect on model outputs. James Grimmelmann says the paper gives reason to think attribution may fail for what he calls “interesting models.”. Lies 3 Standpunkte mit Belegen und Links zu den Originalquellen.
Zheng Dai says that if removing a piece of training data leaves the model’s output unchanged, that piece of data did not affect the output.
Unterstützendes Moment lesen · Paragraph 4 — quotation 2David Gifford describes the paper’s method as deleting training inputs and all their influence. He says it enables efficient, large-scale deletion and shows that the results do not change.
Unterstützendes Moment lesen · Paragraph 5 — quotation 3James Grimmelmann says the paper gives reason to think attribution will fail for “interesting models,” and that technologists and courts will need other ways to assess copying.
Unterstützendes Moment lesen · Paragraph 19 — quotation 3Zugeordnete Passagen mit dem Kontext zur Überprüfung. Öffnen Sie den Originaltext, um die Quelle zu prüfen.
Originalauszug
this paper provides reason to think that attribution will fail for interesting models
“But . Instead, technologists and courts will need to resort to other methods for assessing copying.”
Originalauszug
If you take away a piece of data and the output of the model doesn’t change, then that piece of data didn’t affect the output
" ,"
Originalauszug
This paper introduces the first method that is absolute. You're actually deleting the inputs and deleting all influences of the inputs.
"They really could not absolutely show that deleting individual things did not change the output. This is the first exact method for doing large-scale deletion efficiently and showing that the results don't change."
Diese Standpunkte sind mit ihren Originalquellen verknüpft. Paraphrasen sind gekennzeichnet und keine wörtlichen Zitate.
Transkript oder Quellenmaterial öffnen (wird in einem neuen Tab geöffnet)Ein Problem melden