SLogic introduces a subgraph-informed approach to logical rule learning for knowledge graph completion, assigning query-dependent scores to rules instead of a single global weight. The framework uses a context-aware scoring function that evaluates the importance of a rule based on the local subgraph around the query’s head entity, aligning with the specificity principle of commonsense reasoning. Experiments on benchmark datasets demonstrate that SLogic performs competitively with other rule-based methods while producing human-readable, query-specific explanations.
By Trung Hoang Le, Tran Cao Son, Ishtiaq Ahmed, Huiping Cao
The paper introduces the Structure-Internalized Rule Language Model (SIRLM) to improve Knowledge Graph Reasoning (KGR) by addressing the mismatch between KG structural context and Large Language Model (LLM) parametric knowledge. SIRLM centers on a Structure-Internalized Rule Generator (SIRG) that uses in-context learning, a structural relation memory, a KG tokenizer, and a neuro-symbolic reasoner to generate structural rules and provide faithful rule-execution feedback. Experiments on 36 datasets against 17 state‑of‑the‑art KGR methods show that SIRLM achieves significant performance gains.
By Xingrui Zhuo, Jiapu Wang, Manzong Huang, Gongqing Wu, Xindong Wu
arXiv:2607. 19996v1 Announce Type: new Abstract: Machine Learning models are widely used for automating classification tasks by extracting statistical patterns from data.
By Yousef Khan, Luca Gherardini, Marco Maratea, Joel Arrais, Jose Sousa
arXiv:2508. 10971v2 Announce Type: replace-cross Abstract: Knowledge graphs (KGs) can be enhanced through rule mining; however, the resulting logical rules are often difficult for humans to interpret due to their inherent complexity and the idiosyncratic labeling conventions of individual KGs.
By Nasim Shirvani-Mahdavi, Chengkai Li
arXiv:2508. 06706v2 Announce Type: replace Abstract: Rule-based methods for knowledge graph completion provide explainable results, but often require tens of thousands of rules to achieve competitive performance.
By Jaikrishna Manojkumar Patil, Nathaniel Lee, Al Mehdi Saadat Chowdhury, YooJung Choi, Paulo Shakarian
The paper introduces a logic-based framework that extracts global logical rules for node classification in Simple Graph Convolution (SGC) networks. It uses minimal abductive explanations—small sets of node-feature pairs that preserve a node’s predicted class—as an intermediate step. Decision trees trained on these explanations yield compact global rules that retain high fidelity to the original SGC model, as demonstrated on benchmark datasets.
By Bryan Lima Cavalcante, Thiago Alves Rocha
arXiv:2510. 19698v3 Announce Type: replace Abstract: Large Language Models (LLMs) can propose rules in natural language, sidestepping the need for a predefined predicate space in traditional rule learning.
By Yang Yang, Hua XU, Zhangyi Hu, Yutao Yue
arXiv:2608.30250v1 Announce Type: new
Abstract: This paper addresses the problem of translating natural-language routing rules written by business administrators into executable workflow graphs for e...
By Anand Iyer, Bhanu Khetharpal, Srinivas Upadhya, Ramkumar Rajagopal
arXiv:2608.22753v1 Announce Type: new
Abstract: Large language models (LLMs) excel at text understanding and generation, yet still struggle to reliably understand and apply externally provided proced...
By Bohan Yu, Pengfei Cao, Chen Han, Chenxi Zhou, Zhiheng Zhang, Zhiyang Xie, Wenhao Teng, Xiangwen Liao, Jun Zhao, Kang Liu
arXiv:2512. 01113v2 Announce Type: replace-cross Abstract: Algorithmic reasoning -- the ability to perform step-by-step logical inference -- is a synthetic benchmark for evaluating multi-step reasoning abilities, designed for graph neural networks and also for transformer models.
By Dongyue Li, Zhenshuo Zhang, Minxuan Duan, Edgar Dobriban, Hongyang R. Zhang
arXiv:2509. 24256v2 Announce Type: replace-cross Abstract: The pretrain-transfer paradigm, which underpins the success of large language models (LLMs), has demonstrated the immense power of creating foundation models that learn generalizable representations from vast datasets.
By Yunhao Liang, Pujun Zhang, Yuan Qu, Jingyuan Yang, Shaochong Lin, Zuo-jun Max Shen
GraphCert introduces a method to bootstrap graph reasoning agents by generating graph‑grounded question‑answer pairs and certifying the supporting evidence. The approach uses a Bootstrapped Graph Quizzer to produce QA pairs, then executes and semantically curates the evidence into certified rubrics that guide reward‑based training of a Graph Solver. Experiments on five GRBENCH domains show GraphCert outperforms larger LLM agents and demonstrates robust policy transfer across heterogeneous graphs.
By Weiqi Jiang, Yuchen Ying, Rui Wang, Kaixuan Chen, Bingde Hu, Shunyu Liu, Yu Wang, Tongya Zheng