Template-based approaches have advanced Event Argument Extraction (EAE) by formulating it as a structured prediction problem. However, existing methods mainly rely on either fixed manually designed templates, which suffer from template under-matching in diverse contexts, or exhaustive enumeration of template permutations, incurring prohibitively high computational cost. Moreover, they often overlook the semantic heterogeneity across events. To address these challenges, we propose ATSR, an Adaptive Template Selection and Role-Aware Routing framework for document-level multi-event EAE, integrating an Adaptive Multi-structure Template Selection (AMSTS) module and a Role-Aware Mixture-of-Experts (RAMoE) module. Specifically, AMSTS leverages a set of pre-defined multi-structure templates for each event type and adaptively selects the most compatible one for each event based on learnable weights conditioned on trigger representations. The RAMoE operates over template-aligned slots and routes each role to specialized experts for event semantic modeling. Extensive experiments on three benchmark datasets demonstrate that ATSR achieves state-of-the-art performance with competitive efficiency, while remaining effective in few-shot settings.

Current rumor detectors exhibit limitations in fully exploiting responses to the source tweet as essential public opinions, and in explaining and indicating the reliability of the results obtained. Additionally, the joint utilization of both responses and the multimodal source content for detection presents challenges due to the heterogeneous nature of the data points. In this work, to address the first challenge, we initially prompt the Large Language Model (LLM) with both multimodal source content and the corresponding response set to extract contrasting evidence to enable maximal utilization of informative responses. To overcome the second challenge, we introduce an uncertainty-aware evidential evaluator to assess the evidence intensity from the multimodal source content and dual-sided reasoning, from which the final prediction is derived. As we model the second-order probability, we can effectively indicate the model’s uncertainty (i.e., the reliability) of the results. The reasoning from the correct perspective also serves as a natural language-based explanation. To this end, the third challenge is also addressed as we fully leverage the available resources. Extensive experiments validate the effectiveness, uncertainty awareness in predictions, helpful explainability for human judgment, and superior efficiency of our approach compared to contemporary works utilizing LLMs.