MERIT‑Rank is a reranking framework that integrates multiple reasoning trajectories to enhance text ranking robustness. It introduces a Multi‑Trajectory Reasoning Space (MTRS) to evaluate query‑document relevance from diverse perspectives and a joint reranker that consolidates these paths into a single ranking decision. The Progressive Rank Policy Optimization (PRPO) training scheme stabilizes reasoning trajectories and progressively improves ranking quality, yielding superior performance on both reasoning‑intensive and traditional retrieval benchmarks, with a 4B model outperforming larger 7B and 32B rerankers on BRIGHT.
By Lijun Liu, Zhengzong Chen, Wenyan Li, Yuanyuan Zhao, Fei Huang
MERIT‑Rank introduces a multi‑trajectory reasoning framework for text reranking, combining complementary reasoning paths to enhance robustness against errors. It defines a Multi‑Trajectory Reasoning Space (MTRS) and a joint reranker that merges these perspectives into a single ranking decision. The Progressive Rank Policy Optimization (PRPO) training scheme stabilizes reasoning trajectories and progressively improves ranking quality, yielding superior performance on both reasoning‑intensive and traditional retrieval benchmarks, with a 4B model outperforming larger rerankers on BRIGHT.
arXiv:2607. 25182v1 Announce Type: cross Abstract: The ability to retrieve relevant tables for answering questions is a key task for structured information retrieval.
By Adarsh Singh, Kushal Raj Bhandari, Jianxi Gao, Soham Dan, Vivek Gupta
arXiv:2605. 04495v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) relies on evidence ranking to determine what information is exposed to the generator, yet existing retrieval and reranking methods primarily estimate query--document relevance.
By Zhipeng Song, Yizhi Zhou, Xiangyu Kong, Jiulong Jiao, Xuezhou Ye, Chunqi Gao, Xueqing Shi, Yu Wang, Yuhang Zhou, Heng Qi
Glance is a retrieval‑augmented generation approach that eliminates the need for separate reranker models by adding a lightweight decision adapter and pointer head to a single 9B backbone. It scores candidate passages directly from a shared prefill, requiring only about 0.1 GiB of extra memory per decision skill. In fine‑tuning on MS MARCO, Glance outperforms the bge‑reranker‑v2‑m3 on SciFact and NFCorpus, and improves answer F1 on HotpotQA by 0.045, while scaling to 200 candidates it surpasses cross‑encoder reranking by 0.058 nDCG@10.
arXiv:2606. 01070v1 Announce Type: cross Abstract: Dense retrievers excel at first-stage candidate generation but lack effective reranking in zero-resource settings.
By Shiyan Liu, Yichen Li