LLMs learn causal relations in text via variational induction by detecting difference-makers in word sequences across diverse training data.
arxiv.org/abs/2401.03910
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Language models encode modal categories via linear difference vectors in their activations that predict fine-grained human plausibility judgments better than prior reports suggested.
Supervised learning across AI systems vindicates a uniform error-driven associationism for cognition, though operating inside advanced computational structures beyond classical associationist models.
citing papers explorer
-
Words as Difference Makers: How Large Language Models Determine Causal Structure in Text
LLMs learn causal relations in text via variational induction by detecting difference-makers in word sequences across diverse training data.
-
Is This Just Fantasy? Language Model Representations Reflect Human Judgments of Event Plausibility
Language models encode modal categories via linear difference vectors in their activations that predict fine-grained human plausibility judgments better than prior reports suggested.
-
The New Associationism: Lessons from Deep Learning
Supervised learning across AI systems vindicates a uniform error-driven associationism for cognition, though operating inside advanced computational structures beyond classical associationist models.