Reading Between the Timelines: RAG for Answering Diachronic Questions

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lau, Kwun Hang, Zhang, Ruiyuan, Shi, Weijie, Zhou, Xiaofang, Cheng, Xiaojun
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909712670261248
author Lau, Kwun Hang
Zhang, Ruiyuan
Shi, Weijie
Zhou, Xiaofang
Cheng, Xiaojun
author_facet Lau, Kwun Hang
Zhang, Ruiyuan
Shi, Weijie
Zhou, Xiaofang
Cheng, Xiaojun
contents While Retrieval-Augmented Generation (RAG) excels at injecting static, factual knowledge into Large Language Models (LLMs), it exhibits a critical deficit in handling longitudinal queries that require tracking entities and phenomena across time. This blind spot arises because conventional, semantically-driven retrieval methods are not equipped to gather evidence that is both topically relevant and temporally coherent for a specified duration. We address this challenge by proposing a new framework that fundamentally redesigns the RAG pipeline to infuse temporal logic. Our methodology begins by disentangling a user's query into its core subject and its temporal window. It then employs a specialized retriever that calibrates semantic matching against temporal relevance, ensuring the collection of a contiguous evidence set that spans the entire queried period. To enable rigorous evaluation of this capability, we also introduce the Analytical Diachronic Question Answering Benchmark (ADQAB), a challenging evaluation suite grounded in a hybrid corpus of real and synthetic financial news. Empirical results on ADQAB show that our approach yields substantial gains in answer accuracy, surpassing standard RAG implementations by 13% to 27%. This work provides a validated pathway toward RAG systems capable of performing the nuanced, evolutionary analysis required for complex, real-world questions. The dataset and code for this study are publicly available at https://github.com/kwunhang/TA-RAG.
format Preprint
id arxiv_https___arxiv_org_abs_2507_22917
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Reading Between the Timelines: RAG for Answering Diachronic Questions
Lau, Kwun Hang
Zhang, Ruiyuan
Shi, Weijie
Zhou, Xiaofang
Cheng, Xiaojun
Computation and Language
Artificial Intelligence
Information Retrieval
While Retrieval-Augmented Generation (RAG) excels at injecting static, factual knowledge into Large Language Models (LLMs), it exhibits a critical deficit in handling longitudinal queries that require tracking entities and phenomena across time. This blind spot arises because conventional, semantically-driven retrieval methods are not equipped to gather evidence that is both topically relevant and temporally coherent for a specified duration. We address this challenge by proposing a new framework that fundamentally redesigns the RAG pipeline to infuse temporal logic. Our methodology begins by disentangling a user's query into its core subject and its temporal window. It then employs a specialized retriever that calibrates semantic matching against temporal relevance, ensuring the collection of a contiguous evidence set that spans the entire queried period. To enable rigorous evaluation of this capability, we also introduce the Analytical Diachronic Question Answering Benchmark (ADQAB), a challenging evaluation suite grounded in a hybrid corpus of real and synthetic financial news. Empirical results on ADQAB show that our approach yields substantial gains in answer accuracy, surpassing standard RAG implementations by 13% to 27%. This work provides a validated pathway toward RAG systems capable of performing the nuanced, evolutionary analysis required for complex, real-world questions. The dataset and code for this study are publicly available at https://github.com/kwunhang/TA-RAG.
title Reading Between the Timelines: RAG for Answering Diachronic Questions
topic Computation and Language
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2507.22917