ReaLM: Residual Quantization Bridging Knowledge Graph Embeddings and Large Language Models

ArXi:2510.09711v2 Announce Type: replace Large Language Models (LLMs) have recently emerged as a powerful paradigm for Knowledge Graph Completion (KGC), offering strong reasoning and generalization capabilities beyond traditional embedding-based approaches. However, existing LLM-based methods often struggle to fully exploit structured semantic representations, as the continuous embedding space of pretrained KG models is fundamentally misaligned with the discrete token space of LLMs. This discrepancy hinders effective semantic transfer and limits their performance.