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
Neural models in high-stakes domains lack access to ontological domain constraints that practitioners take for granted, and retrofitting such knowledge is hard: expressive logical formalisms do not scale, while scalable ones cannot express the negation, disjunction, and quantification that real constraints require. We present a differentiable reasoning framework that resolves this tension. Operating within a decidable logic that retains full Boolean expressivity, it transforms domain rules into a training objective with guaranteed polynomial-time cost per iteration. 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. This finding motivates two adaptive mechanisms: a semantic gate that focuses gradient signal on the model's most flagrant logical violations, and a structure-aware loss that automatically reweights its objective according to the logical complexity of the input constraints. Together, they eliminate the need for per-dataset loss tuning. On eight benchmark ontologies, the framework achieves statistically significant improvements over nine baselines spanning neuro-symbolic, geometric, and probabilistic paradigms. On semantic image interpretation, it refines a frozen object detector using domain rules alone - without the need for extra labels - lifting macro-averaged F1 by up to 7.8%, showing that structured knowledge, properly injected, can turn brittle pattern-matching into logically coherent prediction.
Zi-Han Shao, Chang Lu, Renate A. Schmidt et al.· Proceedings of the 32nd ACM...· 0 citations
Prototype-based neural networks are hailed as interpretable-by-design architectures. Recently, Abductive Latent Explanations (ALE) were introduced to provide formal, mathematically guaranteed explanations that leverage the intrinsic structure of these networks to ensure both predictive safety and human readability. ALEs rely on computing tight bounds on latent space distances to produce formal explanations. However, existing ALE formulations are rigidly confined to Euclidean latent spaces. This leaves a critical gap: modern state-of-the-art architectures increasingly rely on non-Euclidean representations - such as spherical metrics, Gaussian densities, and dimensional projections - rendering current formal explanation methods incompatible. In this work, we generalize the ALE framework to support non-Euclidean prototype architectures. For each geometric variant, we systematically derive how to either map the architecture to existing bounds or construct novel, architecture-specific bounding algorithms. We validate our theoretical constructions by computing subset-minimal formal explanations on fully trained image classifiers. By unifying these diverse models under a single formal framework, we enable the first rigorous, cross-architecture comparison of their interpretability.
J. Soria, Alban Grastien, Romain Xu-Darme et al.· 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
How humans grow and maintain abstract knowledge from the sparse, streaming noisy data of experience is a longstanding challenge in cognitive science. Any computational account must satisfy at least three desiderata: It must be (1) data-efficient and compute-efficient, (2) capture gradations of uncertainty to support intelligent inquiry and information gathering, and (3) be flexible enough to mentally represent the endless range of concepts people can learn and think about. Here we introduce a computational model that captures these three properties, by encoding symbolic knowledge as mental programs that combine natural language with source code, and sequentially inferring mental programs using LLM-guided Bayesian learning algorithms. Across a range of behavioral studies this model successfully reproduces quantitative signatures of human inductive learning and active inquiry, such as anchoring, garden-pathing, and other effects. In contrast, pure LLMs and classic Bayesian models either fail at the underlying task, or do not reproduce human behavior, or succeed only at exorbitant computational cost. These 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 learnable.
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.
