系统梳理大模型时代长文档检索方法与挑战
A Survey of Long-Document Retrieval in the PLM and LLM Era
- 按时代梳理从传统模型到大模型的长文档检索技术演进
- 总结多阶段检索、层级编码等核心方法及最新进展
- 适合关注信息检索、大模型应用的研究者参考
长篇文档的爆发式增长对信息检索（IR）构成根本性挑战，因其长度、证据分散和复杂结构，需超越标准段落级方法的专门技术。本文首次全面综述长文档检索（LDR），整合三个主要时期的方法、挑战与应用。系统梳理了从经典词法与早期神经模型，到现代预训练模型（PLM）与大语言模型（LLM）的演进历程，涵盖段落聚合、层级编码、高效注意力等关键范式，以及最新的基于大模型的重排序与检索技术。除模型外，还回顾了领域特定应用、专用评估资源，并指出效率权衡、多模态对齐、忠实度等关键开放挑战。本综述旨在为大模型时代推进长文档检索提供整合性参考与前瞻路线。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。