document re-ranking

New Framework Distinguishes Entity Relevance Signals for Improved Document Re-Ranking

A new research paper introduces a framework distinguishing Conceptual Entity Relevance (CER) from Observable Entity Relevance (OER), showing that CER and OER have near-chance agreement. Aligning supervision with OER improves non-relevant document pruning by up to 10x and open-world Mean Average Precision by 0.051 over BM25, challenging assumptions in entity-aware retrieval.