Theoretical analysis of continual factual knowledge acquisition shows data replay stabilizes pretrained knowledge by shifting convergence dynamics while regularization only slows forgetting, leading to the STOC method for attention-based replay selection.
AI Open , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A small set of sparse autoencoder features in LLMs drives shifts between generous and selfish allocations in dictator games, with causal patching and steering confirming their role and generalization to other social games.
citing papers explorer
-
Towards Understanding Continual Factual Knowledge Acquisition of Language Models: From Theory to Algorithm
Theoretical analysis of continual factual knowledge acquisition shows data replay stabilizes pretrained knowledge by shifting convergence dynamics while regularization only slows forgetting, leading to the STOC method for attention-based replay selection.
-
Understanding the Mechanism of Altruism in Large Language Models
A small set of sparse autoencoder features in LLMs drives shifts between generous and selfish allocations in dictator games, with causal patching and steering confirming their role and generalization to other social games.