{"ID":2873052,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.07759","arxiv_id":"2509.07759","title":"A Survey of Long-Document Retrieval in the PLM and LLM Era","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2509.07759","url_pdf":"https://arxiv.org/pdf/2509.07759v2","authors":"[\"Minghan Li\",\"Miyang Luo\",\"Tianrui Lv\",\"Yishuai Zhang\",\"Siqi Zhao\",\"Ercong Nie\",\"Guodong Zhou\"]","published":"2025-09-09T13:57:53Z","proceeding":"cs.IR","tasks":"[\"cs.IR\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}