Skip to content

LLM-RDO: Large Language Model-Guided Rules Dynamic Optimization for Temporal Knowledge Graph Reasoning

Oct 2026 · IEEE Internet of Things Journal · Vol 13, pp. 45989-46000 · 0 citations · 46 references

Abstract

Temporal knowledge graph reasoning (TKGR) aims to predict future facts based on historical event facts. However, the traditional embedding-based methods lack interpretability and the rule-based methods are prone to falling into spurious correlation traps. Note that the recent large language model (LLM)-based methods are mostly static, open-loop generations lacking dynamic adaptability. This article proposes a novel hybrid reasoning framework, a so-called LLM-guided rule dynamic optimization (LLM-RDO), by integrating the structural robustness captured by graph neural networks (GNNs) into the discrete causal logic optimized by LLM. To extract logically coherent matching rules and the top-<inline-formula> <tex-math notation="LaTeX">$k$ </tex-math></inline-formula> relevant relations, an association rule mining (ARM) algorithm is designed combined with temporal path matching. To generate higher-quality rules, an LLM-guided iterative dynamic feedback loop is constructed to optimize rules by integrating the semantic features of matching rules and top-<inline-formula> <tex-math notation="LaTeX">$k$ </tex-math></inline-formula> relevant relations. Specifically, matching rules and top-<inline-formula> <tex-math notation="LaTeX">$k$ </tex-math></inline-formula> relevant relations are input into LLM to generate rules, which are then interactively scored against current data. High-quality rules are used for subsequent result prediction, while low-quality rules are fed back into LLM for further optimization. Finally, to achieve higher prediction accuracy, a joint prediction mechanism combining rule-based and embedding-based approaches is introduced. Experiments on 4 benchmark datasets demonstrate that LLM-RDO achieves superior performance compared to existing state-of-the-art baseline methods.

View source

Similar papers

Conference Open access Sep 2026

Leveraging Implicit Contexts via LLM–Graph Fusion for Temporal Knowledge Graph Reasoning

Temporal knowledge graph (TKG) reasoning is critical for modeling and forecasting the evolution of real-world events. Existing TKG construction pipelines transform raw text into structured temporal quadruples as graph facts. However, in this process, they often fail to preserve reasoning-relevant contextual semantics f...

Ze-Shu Tian, J. Tao, Hong-Li Zhang · 0 citations
Conference Aug 2026

Introspective Dynamic Strategy for Knowledge Graph Enhanced Reasoning in Large Language Models

Large Language Models (LLMs) achieve strong performance on many tasks, yet their reasoning can remain brittle and their decision process is often insufficiently transparent. Knowledge graphs (KGs) provide explicit entities and relations that can ground reasoning and improve traceability. However, most KG-augmented appr...

Jia-Jun Duan, Qiu-Ling Chen, Ze-Xu Wang et al. · 0 citations
Preprint Aug 2026

SymbolLKG: Towards Verifiable Logical Reasoning via Logical Knowledge Graph and Symbolic Solvers

A Neuro-Symbolic architecture that integrates a Logical Knowledge Graph (LKG) with dynamic solver routing, and introduces an ontology-based LKG that treats logical rules and constraints as first-class topological nodes, enabling explicit modeling of dependencies extracted from text.

Hai-Zhao Fan, Yu-Chi Xiong, Jize Wang et al. · 0 citations
Aug 2026

Structure-aware generative framework for temporal knowledge graph reasoning with historical evidence

AG is proposed, a Structure-Aware Generative framework for temporal knowledge graph reasoning with historical evidence that first constructs dual-view historical evidence to better capture structural dependencies in temporal knowledge graphs and formulates TKGR as an end-to-end generative task through instruction tunin...

Zi-Hao Jiang, Wen-Jie Xu, Miao Peng et al. · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.