GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs

arXiv:2511.11653v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have emerged as powerful tools for passage reranking in information retrieval, leveraging their superior reasoning capabilities to address the limitations of conventional models on complex queries. However, current LLM-based reranking paradigms are fundamentally constrained by an efficiency-accuracy trade-off: (1) pointwise methods are efficient but ignore inter-document comparison, yielding suboptimal accurac