"transformer generalization" Papers
3 papers found
Conference
Generalizing Reasoning Problems to Longer Lengths
Changnan Xiao, Bing Liu
ICLR 2025
4
citations
On the Bias of Next-Token Predictors Toward Systematically Inefficient Reasoning: A Shortest-Path Case Study
Riccardo Alberghi, Elizaveta Demyanenko, Luca Biggio et al.
NEURIPS 2025arXiv:2507.05362
1
citations
On the Minimal Degree Bias in Generalization on the Unseen for non-Boolean Functions
Denys Pushkin, Raphaël Berthier, Emmanuel Abbe
ICML 2024arXiv:2406.06354