The proliferation of long-form documents presents a fundamental challenge to information retrieval (IR), as their length, dispersed evidence, and complex structures demand specialized methods beyond standard passage-level techniques. This survey provides the first comprehensive treatment of long-document retrieval (LDR), consolidating methods, challenges, and applications across three major eras. We systematize the evolution from classical lexical and early neural models to modern pre-trained (PLM) and large language models (LLMs), covering key paradigms like passage aggregation, hierarchical encoding, efficient attention, and the latest LLM-driven re-ranking and retrieval techniques. Beyond the models, we review domain-specific applications, specialized evaluation resources, and outline critical open challenges such as efficiency trade-offs, multimodal alignment, and faithfulness. This survey aims to provide both a consolidated reference and a forward-looking agenda for advancing long-document retrieval in the era of foundation models.
@article{arxiv.2509.07759,
title = {A Survey of Long-Document Retrieval in the PLM and LLM Era},
author = {Minghan Li and Miyang Luo and Tianrui Lv and Yishuai Zhang and Siqi Zhao and Ercong Nie and Guodong Zhou},
journal= {arXiv preprint arXiv:2509.07759},
year = {2025}
}