A single-layer transformer memorizes random subject-attribute bijections using logarithmic embedding dimension via linear superpositions in embeddings and ReLU-gated selection in the MLP, with zero-shot transfer to new facts and matching multi-hop constructions.
arXiv preprint arXiv:2404.05405 , year =
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6representative citing papers
Multi-source transfer learning incurs an intrinsic adaptation cost that can exceed one, with phase transitions separating regimes where bias-agnostic estimators match oracle performance from those where they cannot.
Winner-take-all linear memory capacity scales as d² ~ n log n due to extreme values; listwise retrieval via Tail-Average Margin yields d² ~ n with exact asymptotic theory.
Synthetic pre-pre-training on structured data improves LLM robustness to noisy pre-training, matching baseline loss with up to 49% fewer natural tokens for a 1B model.
Loss-based pruning of training data to limit facts and flatten their frequency distribution enables a 110M-parameter GPT-2 model to memorize 1.3 times more entity facts than standard training, matching a 1.3B-parameter model on the full dataset.
Grokking emerges near the model size where memorization timescale T_mem(P) intersects generalization timescale T_gen(P) on modular arithmetic.
citing papers explorer
-
The Statistical Cost of Adaptation in Multi-Source Transfer Learning
Multi-source transfer learning incurs an intrinsic adaptation cost that can exceed one, with phase transitions separating regimes where bias-agnostic estimators match oracle performance from those where they cannot.
-
Sharp Capacity Thresholds in Linear Associative Memory: From Winner-Take-All to Listwise Retrieval
Winner-take-all linear memory capacity scales as d² ~ n log n due to extreme values; listwise retrieval via Tail-Average Margin yields d² ~ n with exact asymptotic theory.
-
Synthetic Pre-Pre-Training Improves Language Model Robustness to Noisy Pre-Training Data
Synthetic pre-pre-training on structured data improves LLM robustness to noisy pre-training, matching baseline loss with up to 49% fewer natural tokens for a 1B model.
-
Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds
Grokking emerges near the model size where memorization timescale T_mem(P) intersects generalization timescale T_gen(P) on modular arithmetic.