question
active
question:if-we-train-a-model-twice-to-what-extent-do-we-get-the-same-featuresIf we train a model twice, to what extent do we get the same features?
Fresh-traction question.
Source paper
extracted_fromRelated by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- How do features change over model training; do they form abruptly or gradually, and do their directions drift?question0.803Fresh-traction question.
- Core goal statement.
- Fresh-traction question.
- Opening question.
- Are there model structures that account for memorization and generalization across large swaths of training data?question0.772Aggregate analysis motivation.
- How does different post-training data shift a model's position along persona dimensions?question0.770Future work direction: using persona space to study effects of training data on model character
- Authors take agnostic position on ontological status but universality evidence pushes toward features being real
- Future direction.