Elamur Research⌕
☰
home / papers / 2026 / ChunQiuTR: Time-Keyed Temporal Retrieval in Classical Chinese Annals

ChunQiuTR: Time-Keyed Temporal Retrieval in Classical Chinese Annals

Paper · 2026 · Yihao Wang, Zijian He, Jie Ren et al.

Summary

Historical RAG systems need the passage for a specific regnal month, not just any topically related passage. This is hard for Classical Chinese annals. Dates there are given relative to the ruling duke, often in abbreviated form, and must be inferred from context. As a result, semantically similar text from a neighbouring month, or commentary that merely repeats the date, can mislead a retriever.

The authors build ChunQiuTR, a benchmark drawn from the Spring and Autumn Annals (Chunqiu) and its three classical commentaries. Records are indexed by month-level reign keys, and the benchmark includes historically grounded near-miss negatives. LLMs only proposed candidate splits and alignments; humans verified the final data.

They also propose CTD (Calendrical Temporal Dual-encoder), which adds two time signals to semantic matching:

  • a Fourier-based absolute calendrical context injected into embeddings;
  • a relative bias on similarity scores derived from signed calendar offsets.

CTD consistently beats strong semantic dual-encoder baselines, especially against adjacent-month and lexical-near distractors. The work frames temporal consistency at retrieval time as a prerequisite for trustworthy historical RAG.

Key points

  • Time keys: Records are keyed as τ = (gong, year, month) over the Lu chronicle (722–481 BCE). Months without an annals entry receive standardized no_event placeholders.
  • Query design: ChunQiuTR supports point, gap and window queries with leak-free splits. Hard negatives are chrono-near paraphrases from later historiographical layers that share the same key.
  • Curation scale: There are 1,533 non-empty months, 558 of which contain multiple events. After LLM-assisted grouping, only 63 of these needed extra human correction.
  • Ablation results: Gains over the fine-tuned baseline come from the multi retrieval objective, the relative-time logit bias and the absolute temporal context, with the two time components adding up. The extracted table is garbled, so which score is MRR@10 is uncertain; the full model raises the two reported test scores from 0.5771 to 0.5923 and from 0.6044 to 0.6194 (about +0.015 each).
  • Limitations and availability: The scope is a single corpus at month granularity. Neighbouring-month near-duplicates and genuinely ambiguous cases remain hard. Code and data are at github.com/xbdxwyh/ChunQiuTR.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Sun Yat-sen UniversityGuangzhou · China53 works · 9,185 citations🎓Shaanxi Normal UniversityXi'an · China2 works · 940 citations

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksInformation Systems · 1,437 worksLiterature and Literary Theory · 519 works

🧭 Topics 1Research subjects and languages the work is about.Information retrieval & search · 473 works

Cite

Cite as Yihao Wang, Zijian He, Jie Ren and Keze Wang. 2026. ChunQiuTR: Time-Keyed Temporal Retrieval in Classical Chinese Annals. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.612

@inproceedings{wang2026chunqiutr,
  title = {{ChunQiuTR: Time-Keyed Temporal Retrieval in Classical Chinese Annals}},
  author = {Yihao Wang, Zijian He, Jie Ren and Keze Wang},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.612},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.612}
}

References

43 references, 18 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Jiahuan Cao, Dezhi Peng, Peirong Zhang, Yongxin Shi, Yang Liu, Kai Ding, and Lianwen Jin. 2024. TongGu: Mastering classical Chinese understanding with knowledge-grounded large language models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 4196–4210, Miami, Florida,… find
  2. Yuwei Cao, William Groves, Tanay Kumar Saha, Joel Tetreault, Alejandro Jaimes, Hao Peng, and Philip Yu. 2022. XLTime: A cross-lingual knowledge transfer framework for temporal expression extraction. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 1931–1942, Seattle, U… find
  3. Alejandro Sánchez de Castro, Lourdes Araujo, and Juan Martinez-Romo. 2025. A novel methodology for enhancing cross-language and domain adaptability in temporal expression normalization. Computational Linguistics, 51(4):1303–1335. find
  4. Jianlyu Chen, Shitao Xiao, Peitian Zhang, Kun Luo, Defu Lian, and Zheng Liu. 2024. M3-embedding: Multi-linguality, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. In Findings of the Association for Computational Linguistics: ACL 2024, pages 2318–2335, Bang…
  5. Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In Proceedings of the 37th International Conference on Machine Learning, volume 119 of Proceedings of Machine Learning Research, pages 1597–1607.
  6. PMLR. 2025. Temporal information retrieval via time-specifier model merging. In Proceedings of the 3rd Workshop on Towards Knowledgeable Foundation Models (KnowFM), pages 1–13, Vienna, Austria. Association for Computational Linguistics. find
  7. Wenhu Chen, Xinyi Wang, William Yang Wang, and William Yang Wang. 2021. A dataset for answering time-sensitive questions. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, volume 1. find
  8. Rohan Jha, Bo Wang, Michael Günther, Georgios Mastrapas, Saba Sturua, Isabelle Mohr, Andreas Koukounas, Mohammad Kalim Wang, Nan Wang, and Han Xiao. 2024. Jina-ColBERT-v2: A general-purpose multilingual late interaction retriever. In Proceedings of the Fourth Workshop on Multilingual Representation… find
  9. Ziyang Chen, Erxue Min, Xiang Zhao, Yunxin Li, Xin Jia, Jinzhi Liao, Jichao Li, Shuaiqiang Wang, Baotian Hu, and Dawei Yin. 2025. A question answering dataset for temporal-sensitive retrieval-augmented generation. Scientific Data, 12(1):1855. find
  10. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,…
  11. Bhuwan Dhingra, Jeremy R. Cole, Julian Martin Eisenschlos, Daniel Gillick, Jacob Eisenstein, and William W. Cohen. 2022. Time-aware language models as temporal knowledge bases. Transactions of the Association for Computational Linguistics, 10:257– 273.
  12. Thibault Formal, Benjamin Piwowarski, and Stéphane Clinchant. 2021. Splade: Sparse lexical and expansion model for first stage ranking. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’21, page 2288–2292, New York, NY, USA. As…
  13. Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yixin Dai, Jiawei Sun, Haofen Wang, and Haofen Wang. 2023. Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997, 2(1).
  14. Zhichao Geng, Yiwen Wang, Dongyu Ru, and Yang Yang. 2025. Towards competitive search relevance for inference-free learned sparse retrievers. Preprint, arXiv:2411.04403. — [arXiv:2411.04403](https://arxiv.org/abs/2411.04403) find
  15. Arianna Graciotti, Leonardo Piano, Nicolas Lazzari, Enrico Daga, Rocco Tripodi, Valentina Presutti, and Livio Pompianu. 2025. KE-MHISTO: Towards a multilingual historical knowledge extraction benchmark for addressing the long-tail problem. In Findings of the Association for Computational Linguistics… find
  16. SeungYoon Han, Taeho Hwang, Sukmin Cho, Soyeong Jeong, Hoyun Song, Huije Lee, and Jong C. Park. find
  17. Junfeng Kang, Rui Li, Qi Liu, Yanjiang Chen, Zheng Zhang, Junzhe Jiang, Heng Yu, and Yu Su. 2025. PQR: Improving dense retrieval via potential query modeling. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13455–13469, Vienna… find
  18. Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense passage retrieval for open-domain question answering. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6769–6781, Onli…
  19. Omar Khattab and Matei Zaharia. 2020. Colbert: Efficient and effective passage search via contextualized late interaction over bert. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’20, page 39–48, New York, NY, USA. Associati…
  20. Natalia Korchagina. 2016. Building a gold standard for temporal entity extraction from medieval german texts. In "2016 Conference on Language Technologies and Digital Humanities". find
  21. Yibin Lei, Liang Ding, Yu Cao, Changtong Zan, Andrew Yates, and Dacheng Tao. 2023. Unsupervised dense retrieval with relevance-aware contrastive pre-training. In Findings of the Association for Computational Linguistics: ACL 2023, pages 10932–10940, Toronto, Canada. Association for Computational Lin… find
  22. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, and Douwe Kiela. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. In Advances in Neural Information Proc…
  23. Xiaoyan Li and W. Bruce Croft. 2003. Time-based language models. In Proceedings of the Twelfth International Conference on Information and Knowledge Management, CIKM ’03, page 469–475, New York, NY, USA. Association for Computing Machinery. find
  24. Zehan Li, Xin Zhang, Yanzhao Zhang, Dingkun Long, Pengjun Xie, and Meishan Zhang. 2023. Towards general text embeddings with multi-stage contrastive learning. Preprint, arXiv:2308.03281.
  25. Yang Liu, Lan Lan, Jiahuan Cao, Hiuyi Cheng, Kai Ding, and Lianwen Jin. 2025. Large-scale corpus construction and retrieval-augmented generation for Ancient Chinese poetry: New method and data insights. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 779–817, Albuquer… find
  26. Jacob Menick, Maja Trebacz, Vladimir Mikulik, John Aslanides, Francis Song, Martin Chadwick, Mia Glaese, Susannah Young, Lucy Campbell-Gillingham, Geoffrey Irving, and 1 others. 2022. Teaching language models to support answers with verified quotes. arXiv preprint arXiv:2203.11147.
  27. Jianmo Ni, Gustavo Hernandez Abrego, Noah Constant, Ji Ma, Keith Hall, Daniel Cer, and Yinfei Yang. 2022a. Sentence-t5: Scalable sentence encoders from pre-trained text-to-text models. In Findings of the Association for Computational Linguistics: ACL 2022, pages 1864–1874, Dublin, Ireland. Associati…
  28. Jianmo Ni, Chen Qu, Jing Lu, Zhuyun Dai, Gustavo Hernandez Abrego, Ji Ma, Vincent Zhao, Yi Luan, Keith Hall, Ming-Wei Chang, and Yinfei Yang. 2022b. Large dual encoders are generalizable retrievers. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 9844…
  29. Bhawna Piryani, Abdelrahman Abdallah, Jamshid Mozafari, Avishek Anand, and Adam Jatowt. 2025. It’s high time: A survey of temporal question answering. Preprint, arXiv:2505.20243. find
  30. Thilina C. Rajapakse. 2023. Dense passage retrieval: Architectures and augmentation methods. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’23, page 3494, New York, NY, USA. Association for Computing Machinery. find
  31. Stephen Robertson and Hugo Zaragoza. 2009. The probabilistic relevance framework: Bm25 and beyond. Found. Trends Inf. Retr., 3(4):333–389. find
  32. Xinjie Shen, Zhichao Geng, and Yang Yang. 2025. Exploring 0 sparsification for inference-free sparse retrievers. In Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’25, page 2572–2576, New York, NY, USA. Association for Computing… find
  33. Xin Su, Phillip Howard, and Steven Bethard. 2025. Transformer-based temporal information extraction and application: A review. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 28822–28841, Suzhou, China. Association for Computational Linguistics. find
  34. Liquid AI Team. 2025. Lfm2 technical report. Preprint, arXiv:2511.23404. — [arXiv:2511.23404](https://arxiv.org/abs/2511.23404) find
  35. Jiexin Wang, Adam Jatowt, Masatoshi Yoshikawa, and Yi Cai. 2023. Bitimebert: Extending pre-trained language representations with bi-temporal information. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’23, page 812–821, New Y… find
  36. Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, and Furu Wei. 2024a. Improving text embeddings with large language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 11897–11916, Bangkok, Thailand. Ass…
  37. Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, and Furu Wei. 2024b. Multilingual e5 text embeddings: A technical report. Preprint, arXiv:2402.05672.
  38. Shitao Xiao, Zheng Liu, Peitian Zhang, and Niklas Muennighoff. 2023. C-pack: Packaged resources to advance general chinese embedding. Preprint, arXiv:2309.07597.
  39. Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul N. Bennett, Junaid Ahmed, and Arnold Overwijk. 2021. Approximate nearest neighbor negative contrastive learning for dense text retrieval. In International Conference on Learning Representations.
  40. Hugo Yèche, Alizée Pace, Gunnar Ratsch, and Rita Kuznetsova. 2023. Temporal label smoothing for early event prediction. In Proceedings of the 40th International Conference on Machine Learning, volume 202 of Proceedings of Machine Learning Research, pages 39913–39938. PMLR. find
  41. Siyue Zhang, Yuxiang Xue, Yiming Zhang, Xiaobao Wu, Anh Tuan Luu, and Chen Zhao. 2025a. Mrag: A modular retrieval framework for time-sensitive question answering. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 3080–3118. find
  42. Yanzhao Zhang, Mingxin Li, Dingkun Long, Xin Zhang, Huan Lin, Baosong Yang, Pengjun Xie, An Yang, Dayiheng Liu, Junyang Lin, Fei Huang, and Jingren Zhou. 2025b. Qwen3 embedding: Advancing text embedding and reranking through foundation models. Preprint, arXiv:2506.05176.
  43. Yuqing Zhang, Baoyi He, Yihan Chen, Hangqi Li, Han Yue, Shengyu Zhang, Huaiyong Dou, Junchi Yan, Zemin Liu, Yongquan Zhang, and Fei Wu. 2024. PhiloGPT: A philology-oriented large language model for Ancient Chinese manuscripts with dunhuang as case study. In Proceedings of the 2024 Conference on Empi… find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/wang-2026-chunqiutr-time-keyed-temporal-retrieval/