NeSySy:可控约束复杂度的神经符号任务合成生成器
Synthetic Neurosymbolic Task Generation with Controlled Constraint Complexity
搞神经符号学习的朋友可以看看这篇:NeSySy 用 Z3、CNFgen、RC2 这些求解器自动生成带逻辑约束的数据集,还能精确调节任务难度。想公平评测约束学习方法,比拼现有固定基准更靠谱。
arXiv 论文提出 NeSySy,一个神经符号学习任务的合成生成器,可同时产出逻辑约束与一致数据集。它支持对约束结构、紧致度、输入依赖性、数据生成与对齐策略等属性做细粒度控制,并能在无限域上使用丰富约束。
技术层面,NeSySy 内置求解器流水线:CNFgen 和 Z3 负责生成并认证约束的可满足性,RC2(MaxSAT)和 Z3(OMT)做约束优化以计算最优修复,保证每个生成样本都满足约束。系统同时支持声明式约束学习和远程监督学习两种范式。
实验覆盖多组约束族,结果表明其参数对任务难度产生系统性且基本独立的影响。作者借此分析约束感知学习方法,识别出显式约束执行有利的场景,以及表达能力足够强的无约束模型可直接从数据中学到约束结构的场景,为学习与逻辑结构的交互提供了可控测试平台。
Synthetic Neurosymbolic Task Generation with Controlled Constraint Complexity
We introduce NeSySy, a synthetic generator for neurosymbolic learning tasks that jointly produces logical constraints and consistent datasets. Unlike existing benchmarks, NeSySy provides fine-grained control over key properties such as constraint structure, tightness, input dependence, and data generation and alignment strategies. In particular, it allows the use of rich constraints over infinite domains, and uses solvers to ensure that the constraints are meaningful and that generated samples satisfy the constraints. We design NeSySy to support both learning with declarative constraints and learning from distant supervision. Across a range of constraint families, we provide evidence that its parameters induce systematic and largely independent effects on task difficulty. Using NeSySy, we study constraint-aware learning methods, identifying regimes where explicit constraint enforcement is beneficial and where expressive unconstrained models can instead learn constraint structure directly from data. Our results establish NeSySy as a controlled testbed for analysing the interaction between learning and logical structure. NeSySy is built around a pipeline that incorporates solvers. Satisfiability checkers (CNFgen and Z3) generate and certify constraints. Constrained optimizers (RC2 for MaxSAT, Z3 for OMT) compute optimal repairs that guarantee every generated sample is consistent.
本条情报归属 AITOP「论文」核心栏目,重点聚焦欧洲人工智能治理与技术生态。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:NeSySy、神经符号学习、Z3、约束求解,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明:本文原始线索采编自「arXiv cs.AI」(@Mykhailo Buleshnyi, Zsolt Zombori, Michael Benedikt),经 AITOP 多维评分管线结构化提炼。