3 papers
cs.CV2025
Provenance Networks: End-to-End Exemplar-Based Explainability
Ali Kayyam, Anusha Madan Gopal, M. Anthony Lewis
We introduce provenance networks, a novel class of neural models designed to provide end-to-end, training-data-driven explainability. Unlike conventional post-hoc methods, provenan…
cs.CL2025
Quantifying Compositionality of Classic and State-of-the-Art Embeddings
Zhijin Guo, Chenhao Xue, Zhaozhen Xu +4
For language models to generalize correctly to novel expressions, it is critical that they exploit access compositional meanings when this is justified. Even if we don't know what…
cs.LG2025
Behavioural vs. Representational Systematicity in End-to-End Models: An Opinionated Survey
Ivan Vegner, Sydelle de Souza, Valentin Forch +2
A core aspect of compositionality, systematicity is a desirable property in ML models as it enables strong generalization to novel contexts. This has led to numerous studies propos…