# dPASP: A Comprehensive Differentiable Probabilistic Answer Set Programming Environment For Neurosymbolic Learning and Reasoning

arXiv: https://arxiv.org/abs/2308.02944 · HTML: https://mlsanity.com/paper/2308.02944/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 5 of its 17 references that are in the map.
- First posted on arXiv 5 Aug 2023.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 5 of 5)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Multi-shot ASP solving with clingo](https://mlsanity.com/paper/1705.09811/) (2017)
- [NeurASP: Embracing Neural Networks into Answer Set Programming](https://mlsanity.com/paper/2307.07700/) (2023)
- [SMProbLog: Stable Model Semantics in ProbLog and its Applications in Argumentation](https://mlsanity.com/paper/2110.01990/) (2021)
- [PASOCS: A Parallel Approximate Solver for Probabilistic Logic Programs under the Credal Semantics](https://mlsanity.com/paper/2105.10908/) (2021)

## Built on by (most cited first, 3 of 3)

- [Sandra -- A Neuro-Symbolic Reasoner Based On Descriptions And Situations](https://mlsanity.com/paper/2402.00591/) (2024)
- [On the use of neurosymbolic AI for defending against cyber attacks](https://mlsanity.com/paper/2408.04996/) (2024)
- [Symbolic Parameter Learning in Probabilistic Answer Set Programming](https://mlsanity.com/paper/2408.08732/) (2024)

## Abstract (arXiv)

We present dPASP, a novel declarative probabilistic logic programming framework for differentiable neuro-symbolic reasoning. The framework allows for the specification of discrete probabilistic models with neural predicates, logic constraints and interval-valued probabilistic choices, thus supporting models that combine low-level perception (images, texts, etc), common-sense reasoning, and (vague) statistical knowledge. To support all such features, we discuss the several semantics for probabilistic logic programs that can express nondeterministic, contradictory, incomplete and/or statistical knowledge. We also discuss how gradient-based learning can be performed with neural predicates and probabilistic choices under selected semantics. We then describe an implemented package that supports inference and learning in the language, along with several example programs. The package requires minimal user knowledge of deep learning system's inner workings, while allowing end-to-end training of rather sophisticated models and loss functions.