2604.00639 Directional Selection with Dimensional Control Improves Embedding-Based Matching
Standard embedding-based matching collapses multi-dimensional similarity into a single cosine score, conflating dimensions that users need to query independently. We show that combining directional selection (maximizing similarity along a specified target direction) with orthogonal projection (removing confounding dimensions) produces a three-part matching score that consistently outperforms both naive cosine similarity and projection-alone baselines.