LongRanker: Efficient One-Pass Document Reranking with Long-Context Large Language Models
Open Access
- 12 April 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 2004-2013
Abstract
No abstract availableFunding Information
- The Strategic Priority Research Program of the CAS (No. XDB0680102)
- The National Natural Science Foundation of China (No. 62472408, U25B2076, 62372431 and 62441229)
- the National Key Research and Development Program of China under Grants (No. 2023YFA1011602)
- the Dutch Research Council (NWO) (024.004.022, NWA.1389.20.183, and KICH3.LTP.20.006)
- The European Union (No. 101070212 (FINDHR) and No. 101201510 (UNITE))
This publication has 16 references indexed in Scilit:
- Self-Calibrated Listwise Reranking with Large Language Models2025
- Set-Encoder: Permutation-Invariant Inter-passage Attention for Listwise Passage Re-ranking with Cross-Encoders2025
- A Setwise Approach for Effective and Highly Efficient Zero-shot Ranking with Large Language Models2024
- RoFormer: Enhanced transformer with Rotary Position EmbeddingNeurocomputing, 2023
- Understanding and Predicting User Satisfaction with Conversational Recommender SystemsACM Transactions on Information Systems, 2023
- Squeezing Water from a Stone: A Bag of Tricks for Further Improving Cross-Encoder Effectiveness for Reranking2022
- Pyserini: A Python Toolkit for Reproducible Information Retrieval Research with Sparse and Dense Representations2021
- Document Ranking with a Pretrained Sequence-to-Sequence Model2020
- A new probabilistic model for top-k ranking problem2012
- The Probabilistic Relevance Framework: BM25 and BeyondFoundations and Trends® in Information Retrieval, 2009