Dual-Path LLM Reasoning for Multimodal Few-Shot Knowledge Graph Completion

arXiv:2607.26909v1 Announce Type: new Abstract: Knowledge graph completion (KGC) aims to infer missing facts in knowledge graphs (KGs), thereby improving their completeness and supporting downstream intelligent applications. However, emerging entities and relations in real-world deployments make inductive KGC difficult, especially under few-shot and zero-shot settings. Multimodal information and Large Language Model (LLM)-derived priors can enrich sparse relational contexts, but they may also introduce noisy or hallucinated evidence. To address these issues, we propose DuPLeR, a extbf{Du}al-extbf{P}ath extbf{L}LM extbf{R}easoning framework for multimodal few-shot KGC. DuPLeR builds a calibrated relation graph by combining multimodal LLM-derived type priors with factual support structures, and performs dual-level structural reasoning over the refined relation topology. Moreover, a dual-pathway multimodal enhancement module regulates message passing with query-relevant multimodal signals and supplements entity representations after graph propagation. Experiments on eight inductive variants of two multimodal KG (MMKG) benchmarks show that DuPLeR achieves robust performance in data-scarce KGC scenarios.

Related

• RelBall: Relation Ball with Quaternion Rotation for Knowledge Graph Completion
• CHARM: A Multimodal Graph Foundation Model with Hierarchical Context Modeling for Zero-Shot Transfer
• Collaboration of Fusion and Independence: Hypercomplex-driven Robust Multi-Modal Knowledge Graph Completion

Source: arXiv cs.CL | 2026-07-30