finding
active
finding:on-olmo-7b-historical-quotes-k-fac-reaches-16-1-strict-svd-17-5-bsn-60-0On OLMo-7B Historical Quotes K-FAC reaches 16.1% strict, SVD 17.5%, BSN 60.0%
Better transfer to unseen memorized data.
Source paper
extracted_from(2025) · Merullo, Jack · Vatsavaya, Srihita · Bushnaq, Lucius · Lewis, Owen
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- K-FAC suppresses the broadest range of unseen memorized text without requiring labeled forget datasupportsPractical advantage over BSN.
Related 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.
- Replication at smaller scale.
- K-FAC edit reduces OLMo-7B Dolma strict accuracy from 99.9% to 3.4% (BSN 6.0%, SVD 3.0%)finding0.880Table 1.
- Coherence comparison.
- Regularization effect.
- Disentanglement evidence.
- BSN preserves token ranking slightly better.
- K-FAC edit on ViT-Base drops memorized train accuracy from 81.6% to 3.5%, GT accuracy to 66.5% (SVD 58.9%)finding0.773Table 2.
- Vision disentanglement.