A Survey of Long-Document Retrieval in the PLM and LLM Era

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Minghan, Luo, Miyang, Lv, Tianrui, Zhang, Yishuai, Zhao, Siqi, Nie, Ercong, Zhou, Guodong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911230732533760
author Li, Minghan
Luo, Miyang
Lv, Tianrui
Zhang, Yishuai
Zhao, Siqi
Nie, Ercong
Zhou, Guodong
author_facet Li, Minghan
Luo, Miyang
Lv, Tianrui
Zhang, Yishuai
Zhao, Siqi
Nie, Ercong
Zhou, Guodong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_07759
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Survey of Long-Document Retrieval in the PLM and LLM Era
Li, Minghan
Luo, Miyang
Lv, Tianrui
Zhang, Yishuai
Zhao, Siqi
Nie, Ercong
Zhou, Guodong
Information Retrieval
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.
title A Survey of Long-Document Retrieval in the PLM and LLM Era
topic Information Retrieval
url https://arxiv.org/abs/2509.07759