NDProp learns decision heuristics to compute stable models for ASP and shows improved accuracy and scalability in neuro-symbolic benchmarks compared to solver-dependent approaches.
NeurASP: Embracing Neural Networks into Answer Set Programming , booktitle =
5 Pith papers cite this work, alongside 114 external citations. Polarity classification is still indexing.
5
Pith papers citing it
114
external citations · OpenAlex
citation-role summary
background 1
baseline 1
citation-polarity summary
years
2026 5representative citing papers
A framework mines spatial, functional, and qualitative commonsense constraints from SGG training data and uses them to correct ranked predictions at inference, yielding consistent gains on three benchmarks.
Weighted rules extend stable model semantics to support probabilistic reasoning, model ranking, and statistical inference in answer set programs.
LLM-generated streamliners, filtered and selected by an automated pipeline, give up to 4–5× speedups under a per-instance virtual best encoding on three ASP benchmarks.
ASPEn integrates ASP stable-model semantics with energy-based models for joint discrete-continuous optimisation and end-to-end training on visual reasoning and multi-object tracking.
citing papers explorer
-
Neural Decision-Propagation for Answer Set Programming
NDProp learns decision heuristics to compute stable models for ASP and shows improved accuracy and scalability in neuro-symbolic benchmarks compared to solver-dependent approaches.
-
Visual Commonsense Driven Knowledge Refinements for Scene Graph Generation
A framework mines spatial, functional, and qualitative commonsense constraints from SGG training data and uses them to correct ranked predictions at inference, yielding consistent gains on three benchmarks.
-
Weighted Rules under the Stable Model Semantics
Weighted rules extend stable model semantics to support probabilistic reasoning, model ranking, and statistical inference in answer set programs.
-
Streamliners for Answer Set Programming
LLM-generated streamliners, filtered and selected by an automated pipeline, give up to 4–5× speedups under a per-instance virtual best encoding on three ASP benchmarks.
-
Answer Set Programming Energised! End-to-End Neurosymbolic Reasoning and Learning with ASP and Energy Based Models
ASPEn integrates ASP stable-model semantics with energy-based models for joint discrete-continuous optimisation and end-to-end training on visual reasoning and multi-object tracking.