Re3: Learning to Balance Relevance & Recency for Temporal Information Retrieval

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cao, Jiawei, Ouyang, Jie, Zhou, Zhaomeng, Cheng, Mingyue, Li, Yupeng, Yan, Jiaxian, Liu, Qi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908749162086400
author Cao, Jiawei
Ouyang, Jie
Zhou, Zhaomeng
Cheng, Mingyue
Li, Yupeng
Yan, Jiaxian
Liu, Qi
author_facet Cao, Jiawei
Ouyang, Jie
Zhou, Zhaomeng
Cheng, Mingyue
Li, Yupeng
Yan, Jiaxian
Liu, Qi
contents Temporal Information Retrieval (TIR) is a critical yet unresolved task for modern search systems, retrieving documents that not only satisfy a query's information need but also adhere to its temporal constraints. This task is shaped by two challenges: Relevance, ensuring alignment with the query's explicit temporal requirements, and Recency, selecting the freshest document among multiple versions. Existing methods often address the two challenges in isolation, relying on brittle heuristics that fail in scenarios where temporal requirements and staleness resistance are intertwined. To address this gap, we introduce Re2Bench, a benchmark specifically designed to disentangle and evaluate Relevance, Recency, and their hybrid combination. Building on this foundation, we propose Re3, a unified and lightweight framework that dynamically balances semantic and temporal information through a query-aware gating mechanism. On Re2Bench, Re3 achieves state-of-the-art results, leading in R@1 across all three subsets. Ablation studies with backbone sensitivity tests confirm robustness, showing strong generalization across diverse encoders and real-world settings. This work provides both a generalizable solution and a principled evaluation suite, advancing the development of temporally aware retrieval systems. Re3 and Re2Bench are available online: https://anonymous.4open.science/r/Re3-0C5A
format Preprint
id arxiv_https___arxiv_org_abs_2509_01306
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Re3: Learning to Balance Relevance & Recency for Temporal Information Retrieval
Cao, Jiawei
Ouyang, Jie
Zhou, Zhaomeng
Cheng, Mingyue
Li, Yupeng
Yan, Jiaxian
Liu, Qi
Information Retrieval
Machine Learning
Temporal Information Retrieval (TIR) is a critical yet unresolved task for modern search systems, retrieving documents that not only satisfy a query's information need but also adhere to its temporal constraints. This task is shaped by two challenges: Relevance, ensuring alignment with the query's explicit temporal requirements, and Recency, selecting the freshest document among multiple versions. Existing methods often address the two challenges in isolation, relying on brittle heuristics that fail in scenarios where temporal requirements and staleness resistance are intertwined. To address this gap, we introduce Re2Bench, a benchmark specifically designed to disentangle and evaluate Relevance, Recency, and their hybrid combination. Building on this foundation, we propose Re3, a unified and lightweight framework that dynamically balances semantic and temporal information through a query-aware gating mechanism. On Re2Bench, Re3 achieves state-of-the-art results, leading in R@1 across all three subsets. Ablation studies with backbone sensitivity tests confirm robustness, showing strong generalization across diverse encoders and real-world settings. This work provides both a generalizable solution and a principled evaluation suite, advancing the development of temporally aware retrieval systems. Re3 and Re2Bench are available online: https://anonymous.4open.science/r/Re3-0C5A
title Re3: Learning to Balance Relevance & Recency for Temporal Information Retrieval
topic Information Retrieval
Machine Learning
url https://arxiv.org/abs/2509.01306