This study validates Large Language Models' capability to recognize implicit concepts—methodologies, principles, and patterns that texts embody but do not explicitly name. Through five cross-domain test cases (mathematical proof, algorithm description, economic phenomenon, game theory scenario, quantum physics experiment), we demonstrate that LLMs achieve 100% recall on core implicit concept recognition with 96% overall accuracy. However, LLMs cannot reliably output Wikidata Q-identifiers. We propose LICR (LLM-based Implicit Concept Recognition), a hybrid architecture combining LLM semantic understanding with Wikidata API precise mapping, providing a solution for implicit concept recognition that extends beyond traditional entity linking. Key contributions:1. First formal definition of Implicit Concept Recognition Problem (ICRP)2. Empirical validation of LLM implicit concept recognition capability3. Identification of LLM limitations in arbitrary identifier memory4. Proposal of LLM-API hybrid architecture (LICR) This work establishes prior art for the LICR methodology and architecture.
Liu et al. (Sun,) studied this question.