5 papers
Leaving the Cave by Breaking the Symmetry: Identifiable Structure Can Enable Cross-Lingual Generalization
Frederick Riemenschneider, Anette Frank
Why do multilingual language models generalize across languages even without shared vocabulary? The Platonic Representation Hypothesis posits that models trained on different data,…
Cross-Lingual Generalization and Compression: From Language-Specific to Shared Neurons
Frederick Riemenschneider, Anette Frank
Multilingual language models (MLLMs) have demonstrated remarkable abilities to transfer knowledge across languages, despite being trained without explicit cross-lingual supervision…
The Mystery of Compositional Generalization in Graph-based Generative Commonsense Reasoning
Xiyan Fu, Anette Frank
While LLMs have emerged as performant architectures for reasoning tasks, their compositional generalization capabilities have been questioned. In this work, we introduce a Composit…
Exploring Continual Learning of Compositional Generalization in NLI
Xiyan Fu, Anette Frank
Compositional Natural Language Inference has been explored to assess the true abilities of neural models to perform NLI. Yet, current evaluations assume models to have full access…
Dynamic MOdularized Reasoning for Compositional Structured Explanation Generation
Xiyan Fu, Anette Frank
Despite the success of neural models in solving reasoning tasks, their compositional generalization capabilities remain unclear. In this work, we propose a new setting of the struc…