SOURCE-LINKED INTELLIGENCE

Soft Symbol Grounding for Prototypical Concepts

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Neuro-symbolic models are usually trained with supervision only on final labels, leaving the intermediate concepts unobserved. Since many concept assignments are consistent with a given label, training can predict labels correctly while recovering the wrong concepts, a failure known as a reasoning shortcut. Prototypical networks reduce shortcuts by anchoring each concept to a few labeled examples, but existing methods still couple perception and reasoning through a hand-crafted, task-specific differentiable loss that must be redesigned for every task. We introduce \textbf{Soft-PNet}, which rem

Read original source ↗ Open in workspace

recordType

paper

region

Global