Multimodal Knowledge Graphs (MMKGs) provide structured multimodal grounding for Multimodal Large Language Models (MLLMs), while Multimodal Entity Alignment (MMEA) is essential for integrating heterogeneous MMKGs. However, existing MMEA methods remain vulnerable to noisy modalities and unreliable pseudo-supervision. We propose CRMEA, a large–small collaborative framework for unsupervised MMEA that unifies PTM-based retrieval and MLLM-based reasoning through a closed-loop optimization process. CRMEA introduces a text-centric adaptive cross-modal coordination mechanism to regulate noisy visual evidence, together with a retrieve-and-vote strategy for reliable pseudo-supervision. Extensive experiments show that CRMEA consistently outperforms existing unsupervised MMEA methods and achieves performance competitive with state-of-the-art supervised approaches, while maintaining strong robustness, adaptability across heterogeneous backbones, and substantially improved cost-effectiveness over exhaustive MLLM-based alignment. Code and data are available at https://github.com/nsai-szu/CRMEA.

Medical question answering (QA) is a knowledge-intensive task demanding evidence-based reasoning across diverse sources. Despite the demonstrated efficacy of augmenting large language models (LLMs) with domain-specific knowledge graphs (KGs) for QA tasks, the prevailing single-KG paradigm neglects the benefits of multi-KG complementarity. This paper introduces KGFlow, a novel multi-KG reasoning paradigm that mitigates the incomplete coverage and fragmented evidence of single-KG approaches through three LLM agents. Given a query, Knowledge Explorer extracts relevant knowledge triples in parallel from heterogeneous sources. Graph Aligner then semantically harmonizes these triples into global reasoning paths, which are filtered by Contextual Pruner to preserve the most valuable paths for inference. Extensive experiments show that KGFlow achieves promising performance improvements compared to state-of-the-art techniques on five medical QA datasets. We further observe by cases that the plug-and-play nature of our framework enables its application to diverse KG combinations and multilingual scenarios, resulting in broader knowledge coverage than single-KG approaches.

Biomedical document-level relation extraction poses significant challenges beyond sentence-level tasks, as it necessitates the integration of evidence from entire documents and the ability for coherent cross-sentence reasoning. While pretrained language models (PLMs) demonstrate efficiency in handling local contexts, they often struggle with global dependency modeling. Conversely, large language models (LLMs) exhibit strong reasoning capabilities but tend to generate hallucinations in knowledge-intensive biomedical domains. This paper introduces CoRE, a novel cascade framework that leverages the complementary strengths of PLMs and LLMs through a detect-then-rethink paradigm. The PLM serves as an efficient detector for high-confidence relations, while challenging cases are forwarded to an LLM enhanced with semantic retrieval and iterative reasoning mechanisms. Experimental results on BioRED and CDR datasets show that CoRE achieves substantial improvements over state-of-the-art baselines, validating the effectiveness of the proposed cascade paradigm for complex biomedical relation extraction.

Multilingual biomedical entity linking (MBEL) aims to map language-specific mentions in the biomedical text to standardized concepts in a multilingual knowledge base (KB) such as Unified Medical Language System (UMLS). In this paper, we propose Con2GEN, a prompt-based controllable contrastive generation framework for MBEL, which summarizes multidimensional information of the UMLS concept mentioned in biomedical text into a natural sentence following a predefined template. Instead of tackling the MBEL problem with a discriminative classifier, we formulate it as a sequence-to-sequence generation task, which better exploits the shared dependencies between source mentions and target entities. Moreover, Con2GEN matches against UMLS concepts in as many languages and types as possible, hence facilitating cross-information disambiguation. Extensive experiments show that our model achieves promising performance improvements compared with several state-of-the-art techniques on the XL-BEL and the Mantra GSC datasets spanning 12 typologically diverse languages.