FRESCO: Benchmarking and Optimizing Re-rankers for Evolving Semantic Conflict in Retrieval-Augmented Generation

arXiv:2604.14227v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) is a key approach to mitigating the temporal staleness of large language models (LLMs) by grounding responses in up-to-date evidence. Within the RAG pipeline, re-rankers play a pivotal role in selecting the most useful documents from retrieved candidates. However, existing benchmarks predominantly evaluate re-rankers in static settings and do not adequately assess performance under evolving information -- a cr