ChunQiuTR: Time-Keyed Temporal Retrieval in Classical Chinese Annals

TL;DR

ChunQiuTR introduces a time-keyed retrieval benchmark and a time-aware dual-encoder model for historical Chinese texts, emphasizing temporal consistency in retrieval for improved knowledge grounding.

Contribution

The paper presents ChunQiuTR, a novel benchmark and CTD model that incorporate temporal information for more accurate retrieval in Classical Chinese annals.

Findings

CTD outperforms semantic baselines in time-keyed retrieval tasks.

Temporal consistency significantly improves retrieval accuracy.

The benchmark enables evaluation of time-aware retrieval methods.

Abstract

Retrieval shapes how language models access and ground knowledge in retrieval-augmented generation (RAG). In historical research, the target is often not an arbitrary relevant passage, but the exact record for a specific regnal month, where temporal consistency matters as much as topical relevance. This is especially challenging for Classical Chinese annals, where time is expressed through terse, implicit, non-Gregorian reign phrases that must be interpreted from surrounding context, so semantically plausible evidence can still be temporally invalid. We introduce \textbf{ChunQiuTR}, a time-keyed retrieval benchmark built from the \textit{Spring and Autumn Annals} and its exegetical tradition. ChunQiuTR organizes records by month-level reign keys and includes chrono-near confounders that mirror realistic retrieval failures. We further propose \textbf{CTD} (Calendrical Temporal Dual-encoder), a time-aware dual-encoder that combines Fourier-based absolute calendrical context with relative offset biasing. Experiments show consistent gains over strong semantic dual-encoder baselines under time-keyed evaluation, supporting retrieval-time temporal consistency as a key prerequisite for faithful downstream historical RAG. Our code and datasets are available at \href{https://github.com/xbdxwyh/ChunQiuTR}{\texttt{github.com/xbdxwyh/ChunQiuTR}}.