2026· CI-BD-SOQE@FLoC· pp. 114-115· 0 citations· 10 references
Computer Science
TL;DR
This work introduces space explanations, a logic-based notion of explanation that represents sufficient conditions for a neural network to predict a given class over a (potentially large and geometrically complex) subset of the feature space and demonstrates that the interpolation-based explanations are more meaningful than those computed by state-of-the-art techniques.
It is shown that across a broad class of ANNs trained on diverse tasks, their inference logic can indeed be reformulated as sparse symbolic interactions, and two common mathematical criteria lead to the emergence of such sparse symbolic interactions.
This work formalizes explanations as Halpern-Pearl actual causes, modeling input dependencies using Boolean Structural Causal Models (SCMs), and compute HP causes by applying bound propagation and branch-and-bound techniques, while providing formal guarantees of completeness and minimality.
J. Strobel, Muqsit Azeem, Stefan Leue· 0 citations
The framework is operator-agnostic - it decouples logical structure from the choice of underlying continuous semantics, revealing, through the first controlled comparison of its kind, that this choice alone can swing performance by over 30 points on the same task.
Zi-Han Shao, Chang Lu, Renate A. Schmidt et al.· Proceedings of the 32nd ACM...· 0 citations
By unifying these diverse models under a single formal framework, the first rigorous, cross-architecture comparison of their interpretability is enabled, enabling the first rigorous, cross-architecture comparison of their interpretability.
J. Soria, Alban Grastien, Romain Xu-Darme et al.· Lecture Notes in Computer Sc...· 0 citations
This overview addresses this issue by providing a gentle introduction to RSs, discussing their causes and consequences in intuitive terms, and details methods for dealing with RSs, including mitigation and awareness strategies, and maps their benefits and limitations.
E. Marconato, Samuele Bortolotti, Emile van Krieken et al.· Journal of Artificial Intell...· 1 citation
The results suggest that one way humans continually grow their knowledge is by mentally representing many hypotheses spanning language-like and program-like representations, then revising those hypotheses to approximate Bayesian updates, while a bottom-up neural mechanism (an LLM) makes inference both tractable and lea...
Wasu Top Piriyakulkij, Samuel Acquaviva, Cassidy Langenfeld et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
