CONNECTED THINKING
Knowledge atlas
Follow people, viewpoints and their original evidence.
1 people · 1 sources · 1 viewpoints
IN CONTEXT
Exact deletion method for influence testing
Choose a viewpoint. Follow it back to the conversation.
Gifford describes deleting training inputs and their influence
Equal sectors are reading positions, not rankings.
Showing 1–1 of 1 viewpoints · Newest sources first
Selected viewpoint
Gifford describes deleting training inputs and their influence
David 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.
These are individual perspectives, not a measure of consensus. Source material stays in its original language.
Supporting evidence
Original excerpt
This paper introduces the first method that is absolute. You're actually deleting the inputs and deleting all influences of the inputs.
Context
"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."
Publication dates describe the sources, not changes in belief.