2 papers
cs.LG2025
Circuit Compositions: Exploring Modular Structures in Transformer-Based Language Models
Philipp Mondorf, Sondre Wold, Barbara Plank
A fundamental question in interpretability research is to what extent neural networks, particularly language models, implement reusable functions through subnetworks that can be co…
cs.CL2025
Systematic Generalization in Language Models Scales with Information Entropy
Sondre Wold, Lucas Georges Gabriel Charpentier, Ãtienne Simon
Systematic generalization remains challenging for current language models, which are known to be both sensitive to semantically similar permutations of the input and to struggle wi…