Q-TIE：一种轻量级且可泛化的时间信息检索重排序框架
Q-TIE: A Lightweight and Generalizable Re-ranking Framework for Temporal Information Retrieval
浏览论文内容
中文总结 AI 辅助
Q-TIE提出基于学习的时间意图提取的重排序框架，将查询时间约束映射为统一区间表示，兼顾灵活性与显式约束，在TIR任务上超越现有方法并增强泛化能力。
中文摘要 AI 辅助
随着检索增强生成（RAG）的兴起，时间信息检索（TIR）变得越来越关键。由于时间上不匹配的证据可能极具误导性，TIR旨在检索与查询在语义和时间上均相关的文档。目前出现了两种TIR范式——时间检索器（temporal retrievers）和时间重排序器（temporal re-rankers）——它们在时间相关性建模方式上有所不同。虽然这些范式提供了互补的优势，但我们的分析表明，每种范式单独使用都无法实现稳健的TIR：时间检索器通过学习的表示提供灵活的查询理解，但往往无法显式考虑时间约束；时间重排序器可以更显式地执行此类约束，但往往依赖于预定义的重排序规则。为解决这一问题，我们提出了Q-TIE，一种基于学习的时间意图提取（TIE）的重排序框架。通过引入一个TIE模型，将每个查询的时间约束映射为统一的区间表示（即⟨t_start, t_end⟩），Q-TIE通过基于模型的学习超越了预定义规则，同时将时间约束作为独立信号显式建模——共同实现了每种范式通常需要权衡的目标。实验表明，Q-TIE在时间查询类型上始终优于现有TIR方法，具有更强的泛化能力，并为时间感知的RAG流水线提供了一种轻量级且有效的附加组件。代码：此https URL。
英文摘要
Temporal Information Retrieval (TIR) has been increasingly critical given the rise of Retrieval-Augmented Generation (RAG). Since temporally mismatched evidence can be highly misleading, TIR aims to retrieve documents that are both semantically and temporally relevant to a query. Two TIR paradigms have emerged - temporal retrievers and temporal re-rankers - differing in how temporal relevance is modeled. While these paradigms provide complementary strengths, our analysis reveals that each alone falls short of robust TIR: temporal retrievers provide flexible query understanding via learned representations, but often fail to explicitly account for temporal constraints; temporal re-rankers can enforce such constraints more explicitly, but often rely on predefined re-ranking rules. To address this, we propose Q-TIE, a re-ranking framework based on learned Temporal Intent Extraction (TIE). By introducing a TIE model that maps each query's temporal constraint into a unified interval representation (i.e., $\langle t_{start}, t_{end} \rangle$), Q-TIE generalizes beyond predefined rules via model-based learning while explicitly modeling temporal constraints as a separate signal - jointly achieving what each paradigm typically trades off. Experiments demonstrate that Q-TIE consistently outperforms existing TIR methods with stronger generalizability across temporal query types, and provides a lightweight yet effective add-on for temporally-aware RAG pipelines. Code: https://github.com/ssoy0701/Q-TIE.
发表机构
- Korea Advanced Institute of Science and Technology（韩国科学技术院）
- Sungkyunkwan University（成均馆大学）
机构由 AI 辅助整理，请以论文原文为准。
