Chronological Passage Assembling in RAG framework for Temporal Question Answering

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kim, Byeongjeong, Park, Jeonghyun, Yang, Joonho, Lee, Hwanhee
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912643890020352
author Kim, Byeongjeong
Park, Jeonghyun
Yang, Joonho
Lee, Hwanhee
author_facet Kim, Byeongjeong
Park, Jeonghyun
Yang, Joonho
Lee, Hwanhee
contents Long-context question answering over narrative tasks is challenging because correct answers often hinge on reconstructing a coherent timeline of events while preserving contextual f low in a limited context window. Retrievalaugmented generation (RAG) methods aim to address this challenge by selectively retrieving only necessary document segments. However, narrative texts possess unique characteristics that limit the effectiveness of these existing approaches. Specifically, understanding narrative texts requires more than isolated segments, as the broader context and sequential relationships between segments are crucial for comprehension. To address these limitations, we propose ChronoRAG, a novel RAG framework specialized for narrative texts. This approach focuses on two essential aspects: refining dispersed document information into coherent and structured passages and preserving narrative flow by explicitly capturing and maintaining the temporal order among retrieved passages. We empirically demonstrate the effectiveness of ChronoRAG through experiments on the NarrativeQA and GutenQAdataset, showing substantial improvements in tasks requiring both factual identification and comprehension of complex sequential relationships, underscoring that reasoning over temporal order is crucial in resolving narrative QA.
format Preprint
id arxiv_https___arxiv_org_abs_2508_18748
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Chronological Passage Assembling in RAG framework for Temporal Question Answering
Kim, Byeongjeong
Park, Jeonghyun
Yang, Joonho
Lee, Hwanhee
Computation and Language
Long-context question answering over narrative tasks is challenging because correct answers often hinge on reconstructing a coherent timeline of events while preserving contextual f low in a limited context window. Retrievalaugmented generation (RAG) methods aim to address this challenge by selectively retrieving only necessary document segments. However, narrative texts possess unique characteristics that limit the effectiveness of these existing approaches. Specifically, understanding narrative texts requires more than isolated segments, as the broader context and sequential relationships between segments are crucial for comprehension. To address these limitations, we propose ChronoRAG, a novel RAG framework specialized for narrative texts. This approach focuses on two essential aspects: refining dispersed document information into coherent and structured passages and preserving narrative flow by explicitly capturing and maintaining the temporal order among retrieved passages. We empirically demonstrate the effectiveness of ChronoRAG through experiments on the NarrativeQA and GutenQAdataset, showing substantial improvements in tasks requiring both factual identification and comprehension of complex sequential relationships, underscoring that reasoning over temporal order is crucial in resolving narrative QA.
title Chronological Passage Assembling in RAG framework for Temporal Question Answering
topic Computation and Language
url https://arxiv.org/abs/2508.18748