Metraipolis › archive › dc_889a2086752e
TimelyRAG: Semantic-Temporal Hybrid Retrieval for Time-Critical Question Answering in Overlapping-Evolving Documents — arXiv:2609.11572
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.11572
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T06:28:27.315Z
- SHA-256 of the archived text
056df3925c80740b879bef4db694b6cfc2681338d4ec1cb9b5ef852debeb817b- Stable URL of this page
https://metraipolis.com/documento/dc_889a2086752e
How to cite
TimelyRAG: Semantic-Temporal Hybrid Retrieval for Time-Critical Question Answering in Overlapping-Evolving Documents — arXiv:2609.11572 — arXiv (en), https://arxiv.org/abs/2609.11572 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_889a2086752e (Metraipolis archive dc_889a2086752e, sha256 056df3925c80740b879bef4db694b6cfc2681338d4ec1cb9b5ef852debeb817b)
BibTeX
@misc{dc889a2086752e,
title = {TimelyRAG: Semantic-Temporal Hybrid Retrieval for Time-Critical Question Answering in Overlapping-Evolving Documents — arXiv:2609.11572},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.11572},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_889a2086752e; sha256 056df3925c80740b879bef4db694b6cfc2681338d4ec1cb9b5ef852debeb817b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11572. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Although large language models (LLMs) and retrieval-augmented generation (RAG) have advanced open-domain question answering (QA), they remain unreliable when documents evolve through amendments. Existing time-sensitive retrieval methods address only the disjoint-evolving environment, where each update is an independent snapshot. However, laws, policies, and regulations often operate in overlapping-evolving environments, where amendments override earlier clauses while preserving most content, creating strong semantic overlap across versions. We propose TimelyRAG, a retriever-agnostic framework that incorporates temporal distance into ranking to align queries with version-appropriate documents. We also introduce TimelyQABench, the first benchmark for regulation-heavy domains with overlapping-evolving challenges. Experiments show consistent gains, up to +28.6% in nDCG@10, highlighting the importance of temporal reasoning for reliable QA over evolving documents. All resources are available at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-11 in cs.IR). Categorie arXiv: Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2609.11572 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T06:06:09.969Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).