question
active
question:to-what-degree-do-models-generate-genuinely-new-knowledge-as-opposed-to-simply-reassembling-snippets-of-data-memorized-from-their-training-setsTo what degree do models generate genuinely new knowledge, as opposed to simply reassembling snippets of data memorized from their training sets?
Opening question.
Source paper
extracted_from(2025) · Merullo, Jack · Vatsavaya, Srihita · Bushnaq, Lucius · Lewis, Owen
Neighborhood — ranked by edge-count
Papers (1)
paper
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.
- Are there model structures that account for memorization and generalization across large swaths of training data?question0.815Aggregate analysis motivation.
- Core goal statement.
- Inverse scaling interpretation.
- Future direction.
- Fresh-traction question.
- Models trained directly with asynchronous updates would exhibit even greater robustness than synchronously trained modelshypothesis0.776Hypothesis that motivated the asynchronous robustness comparison experiment
- Author's interpretation of the VTAB alignment results echoing Tolstoy
- The paper's central mechanistic explanation of why narrow fine-tuning causes broad misalignment