ADE: Adaptive Dictionary Embeddings -- Scaling Multi-Anchor Representations to Large Language Models

ArXi:2604.24940v1 Announce Type: new Word embeddings are fundamental to natural language processing, yet traditional approaches represent each word with a single vector, creating representational bottlenecks for polysemous words and limiting semantic expressiveness. While multi-anchor representations have shown promise by representing words as combinations of multiple vectors, they have been limited to small-scale models due to computational inefficiency and lack of integration with modern transformer architectures. We.