Elamur Research⌕
☰
home / papers / 2026 / Temporal Evidence Chain for Temporal Knowledge Graph Question Answering with Large Language Models

Temporal Evidence Chain for Temporal Knowledge Graph Question Answering with Large Language Models

Paper · 2026 · Shihao Liu, Xiaofei Zhou, Bo Wang et al.

Summary

The paper addresses question answering over temporal knowledge graphs (TKGQA), where questions such as "who first visited X after Y" require reasoning along an event timeline. The authors argue that current LLM-based approaches fall short in two ways. RAG-style retrievers match facts by semantic similarity alone and miss linking facts. Agent-style systems can derail after one bad tool call. They propose TECQA, which has three stages:

  1. It parses the question with an LLM to obtain entities, relations and a main entity, then expands a subgraph along explicit graph connectivity.
  2. It finds explicit or implicit temporal anchors and keeps only the K facts temporally closest to each anchor.
  3. It orders the retained facts by temporal distance into a compact evidence chain that is given to the LLM.

Evaluated on MultiTQ and CronQuestions, TECQA reaches state-of-the-art results. The largest gains, up to 45.3% over strong baselines, come on complex questions. The work shows that evidence which is structured and ordered by time, rather than simply retrieved by semantic similarity, is key to multi-step temporal reasoning.

Key points

  • Answer Recall@20: semantic retrieval (bge-base-en-v1.5) saturates near 68% and TimeR4 near 78%, while TECQA reaches 94%.
  • Structure-guided retrieval alone gives 99.33% answer recall. Pruning keeps 94.12% recall with only about 20 quadruples of context on average.
  • Temporal anchors are either explicit (normalized dates such as "April 2005") or implicit (the timestamp of an event mentioned in the question).
  • On the 54,584-question MultiTQ test set, only 159 questions (0.29%) produce an empty subgraph, and 86 of these trace back to wrong main-entity extraction.
  • Stated limitations include dependence on accurate parsing and a temporal-locality assumption that may hurt long-horizon questions. Code is released at github.com/SimonsLiu/TECQA.

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

🏛️Chinese Academy of SciencesBeijing · China194 works · 23,906 citations🎓University of Chinese Academy of SciencesBeijing · China147 works · 8,480 citations🔬Institute of Information EngineeringBeijing · China30 works · 1,411 citations🎓University of International Business and EconomicsBeijing · China7 works · 37 citations

 Fields, topics and concepts

📚 Shelves 4The 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 works

🧭 Topics 2Research subjects and languages the work is about.Question answering · 441 worksKnowledge graphs & ontologies · 192 works

Cite

Cite as Shihao Liu, Xiaofei Zhou, Bo Wang and Geyuan Zhang. 2026. Temporal Evidence Chain for Temporal Knowledge Graph Question Answering with Large Language Models. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-long.1361

@inproceedings{liu2026temporal,
  title = {{Temporal Evidence Chain for Temporal Knowledge Graph Question Answering with Large Language Models}},
  author = {Shihao Liu, Xiaofei Zhou, Bo Wang and Geyuan Zhang},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.1361},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1361}
}

References

32 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Ziyang Chen, Dongfang Li, Xiang Zhao, Baotian Hu, and Min Zhang. 2024. Temporal knowledge question answering via abstract reasoning induction. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4872–4889, Bangkok, Thailand. Assoc… find
  2. Ziyang Chen, Jinzhi Liao, and Xiang Zhao. 2023. Multi-granularity Temporal Question Answering over Knowledge Graphs. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 11378– 11392, Toronto, Canada. Association for Computational… find
  3. Ziyang Chen, Xiang Zhao, Jinzhi Liao, Xinyi Li, and Evangelos Kanoulas. 2022. Temporal knowledge graph question answering via subgraph reasoning. Knowledge-Based Systems, 251:109134. find
  4. Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, Luke Marris, Sam Petulla, Colin Gaffney, Asaf Aharoni, Nathan Lintz, Tiago Cardal Pais, Henrik Jacobsson, Idan Szpektor, Nan-Jiang Jiang, and 3416 other…
  5. DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, and 181 others. 2025a. Deepseek-r1: Incentivizing reasoning capability in l…
  6. DeepSeek-AI, Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, Damai Dai, Daya Guo, Dejian Yang, Deli Chen, Dongjie Ji, Erhang Li, Fangyun Lin, Fucong Dai, and 181 others. 2025b. Deepseek-v3 technical report. Preprint, arXiv:… find
  7. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: pre-training of deep bidirectional transformers for language understanding. In NAACL-HLT (1), pages 4171–4186. Association for Computational Linguistics.
  8. Wentao Ding, Hao Chen, Huayu Li, and Yuzhong Qu. 2023. Semantic Framework based Query Generation for Temporal Question Answering over Knowledge Graphs. Preprint, arxiv:2210.04490. find
  9. Yifu Gao, Linbo Qiao, Zhigang Kan, Zhihua Wen, Yongquan He, and Dongsheng Li. 2024. Two-stage Generative Question Answering on Temporal Knowledge Graph Using Large Language Models. Preprint, arxiv:2402.16568. find
  10. Alberto García-Durán, Sebastijan Dumancic, and Mathias Niepert. 2018. Learning sequence encoders for temporal knowledge graph completion. In EMNLP, pages 4816–4821. Association for Computational Linguistics. find
  11. Zhaoyan Gong, Juan Li, Zhiqiang Liu, Lei Liang, Huajun Chen, and Wen Zhang. 2025. RTQA : Recursive thinking for complex temporal knowledge graph question answering with large language models. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 9864–9881,…
  12. Google DeepMind. 2025. Gemini 3 pro. Accessed: 2026-01-05. find
  13. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, and 542 o… — The Llama 3 Herd of Models
  14. Qianyi Hu, Xinhui Tu, Cong Guo, and Shunping Zhang. 2025. Time-aware ReAct agent for temporal knowledge graph question answering. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 6013–6024, Albuquerque, New Mexico. Association for Computational Linguistics. find
  15. Zhen Jia, Abdalghani Abujabal, Rishiraj Saha Roy, Jannik Strötgen, and Gerhard Weikum. 2018. TEQUILA: Temporal Question Answering over Knowledge Bases. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management, pages 1807–1810, Torino Italy. ACM. find
  16. Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2020. ALBERT: A lite BERT for self-supervised learning of language representations. In ICLR. Open-Review.net.
  17. Yonghao Liu, Di Liang, Mengyu Li, Fausto Giunchiglia, Ximing Li, Sirui Wang, Wei Wu, Lan Huang, Xiaoyue Feng, and Renchu Guan. 2023. Local and global: Temporal question answering via information fusion. In Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJ… find
  18. Costas Mavromatis, Prasanna Lakkur Subramanyam, Vassilis N. Ioannidis, Soji Adeshina, Phillip R. Howard, Tetiana Grinberg, Nagib Hakim, and George Karypis. 2021a. TempoQR: Temporal Question Reasoning over Knowledge Graphs. Preprint, arxiv:2112.05785. — [arXiv:2112.05785](https://arxiv.org/abs/2112.05785) find
  19. Costas Mavromatis, Prasanna Lakkur Subramanyam, Vassilis N. Ioannidis, Soji Adeshina, Phillip R. Howard, Tetiana Grinberg, Nagib Hakim, and George Karypis. 2021b. Tempoqr: Temporal question reasoning over knowledge graphs. Preprint, arXiv:2112.05785. — [arXiv:2112.05785](https://arxiv.org/abs/2112.05785) find
  20. Sumit Neelam, Udit Sharma, Hima Karanam, Shajith Ikbal, Pavan Kapanipathi, Ibrahim Abdelaziz, Nandana Mihindukulasooriya, Young-Suk Lee, Santosh Srivastava, Cezar Pendus, Saswati Dana, Dinesh Garg, Achille Fokoue, G. P. Shrivatsa Bhargav, Dinesh Khandelwal, Srinivas Ravishankar, Sairam Gurajada, Mar… — [arXiv:2109.13430](https://arxiv.org/abs/2109.13430) find
  21. OpenAI. 2025. Introducing GPT-5. Accessed: 2026-01-05. find
  22. Xinying Qian, Ying Zhang, Yu Zhao, Baohang Zhou, Xuhui Sui, and Xiaojie Yuan. 2025. Plan of knowledge: Retrieval-augmented large language models for temporal knowledge graph question answering. Preprint, arXiv:2511.04072. — [arXiv:2511.04072](https://arxiv.org/abs/2511.04072) find
  23. Xinying Qian, Ying Zhang, Yu Zhao, Baohang Zhou, Xuhui Sui, Li Zhang, and Kehui Song. 2024. TimeR 4 : Time-aware retrieval-augmented large language models for temporal knowledge graph question answering. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages… find
  24. Apoorv Saxena, Soumen Chakrabarti, and Partha Talukdar. 2021a. Question Answering Over Temporal Knowledge Graphs. Preprint, arxiv:2106.01515. find
  25. Apoorv Saxena, Soumen Chakrabarti, and Partha Talukdar. 2021b. Question answering over temporal knowledge graphs. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Pape… find
  26. Aditya Sharma, Apoorv Saxena, Chitrank Gupta, Seyed Mehran Kazemi, Partha Talukdar, and Soumen Chakrabarti. 2022. TwiRGCN: Temporally Weighted Graph Convolution for Question Answering over Temporal Knowledge Graphs. Preprint, arxiv:2210.06281. find
  27. Miao Su, Zixuan Li, Zhuo Chen, Long Bai, Xiaolong Jin, and Jiafeng Guo. 2025. Temporal knowledge graph question answering: A survey. Preprint, arXiv:2406.14191. — [arXiv:2406.14191](https://arxiv.org/abs/2406.14191) find
  28. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, and 49 others… — Llama 2: Open Foundation and Fine-Tuned Chat Models
  29. Shitao Xiao, Zheng Liu, Peitian Zhang, and Niklas Muennighoff. 2023. C-pack: Packaged resources to advance general chinese embedding. Preprint, arXiv:2309.07597.
  30. Chao Xue, Di Liang, Pengfei Wang, and Jing Zhang. 2024. Question calibration and multi-hop modeling for temporal question answering. In Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence and Fo… find
  31. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, and 41 others. 2025. Qwen3 technical report. Preprint, arXiv:2505.09388.
  32. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2023. React: Synergizing reasoning and acting in language models. Preprint, arXiv:2210.03629.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/liu-2026-temporal-evidence-chain-temporal-knowledge/