Yongliang Ding

Compress-then-Rank: Faster and Better Listwise Reranking with Large Language Models via Ranking-Aware Passage Compression

Listwise reranking with Large Language Models (LLMs) has emerged as the state-of-the-art approach, consistently establishing new performance benchmarks in passage reranking. However, their practical application faces two critical hurdles: the prohibitive computational overhead and high latency of pr