Academic search engines are essential resources for researchers, enabling the discovery of new work and access to relevant literature. Typically, researchers rely on keyword-based search combined with static filters such as publication date, paper type, and citation count. While useful, these static filters operate on metadata and fail to capture the content of research papers. Platforms such as the Open Research Knowledge Graph (ORKG), which aims to structure research findings, and ORKG ASK, an advanced question-driven search system designed to retrieve precise, contextually relevant information from a large corpus of scholarly articles, also face this limitation. To address the shortcomings of static filtering, we introduce Smart Filters, a novel feature integrated into both ORKG and ORKG ASK, enabling context-aware exploration. Smart Filters adopt a neuro-symbolic approach that combines Knowledge Graphs and Large Language Models to dynamically generate semantic facets from paper content. Evaluation results demonstrate that Smart Filters significantly enhance the user search experience and improve content discovery efficiency, doing so more intuitively and effectively.