Temporal Retrieval-Augmented Generation for Reasoning over Dynamic Knowledge Bases
Keywords:
temporal retrieval-augmented generation; dynamic knowledge bases; temporal indexing; reasoning; governance; robustness; fairness; sustainabilityAbstract
Temporal retrieval-augmented generation (TRAG) extends conventional retrieval-augmented generation from relatively static document collections to dynamic knowledge bases whose contents, validity, authority, and relevance change over time. Conventional systems often treat retrieval as a spatial similarity problem, ranking passages by semantic proximity while giving limited attention to temporal order, provenance, versioning, or the lifecycle of facts. This paper develops a system-level account of TRAG for reasoning over dynamic knowledge bases. It examines architectural choices across ingestion, temporal normalization, indexing, retrieval, fusion, generation, and verification, with emphasis on how time-aware representations alter infrastructure requirements and governance obligations. The discussion considers structural trade-offs among freshness, consistency, completeness, latency, cost, and fairness. It also analyzes temporal reasoning as a socio-technical capability rather than a purely algorithmic one, because validity intervals, source authority, and revision histories are shaped by institutions, policies, and record-keeping practices. The paper further explores robustness and evaluation challenges, including temporal drift, contradictory evidence, adversarial updates, and retrospective correction. Deployment and sustainability concerns are addressed through the lens of storage growth, index maintenance, compute intensity, and long-term maintainability. Governance, privacy, fairness, and policy implications are discussed, particularly when dynamic retrieval systems are used in journalism, medicine, finance, law, and public administration. The paper concludes that TRAG requires integrated design principles that treat time, provenance, and accountability as first-class infrastructure concerns rather than post hoc metadata.
References
1. Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W., Rocktäschel, T., Riedel, S., & Kiela, D. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. Advances in Neural Information Processing Systems, 33, 9459-9474.
2. Karpukhin, V., Oğuz, B., Min, S., Lewis, P., Wu, L., Edunov, S., Chen, D., & Yih, W. (2020). Dense passage retrieval for open-domain question answering. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (pp. 6769-6781). Association for Computational Linguistics.
3. Guu, K., Lee, K., Tung, Z., Pasupat, P., & Chang, M. (2020). Retrieval augmented language model pre-training. In Proceedings of the 37th International Conference on Machine Learning (pp. 3929-3938). PMLR.
4. Izacard, G., & Grave, E. (2021). Leveraging passage retrieval with generative models for open domain question answering. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics (pp. 874-880). Association for Computational Linguistics.
5. Borgeaud, S., Mensch, A., Hoffmann, J., Cai, T., Rutherford, E., Millican, K., van den Driessche, G., Lespiau, J. B., Damoc, B., Clark, A., de Las Casas, D., Guy, A., Menick, J., Ring, R., Hennigan, T., Huang, S., Maggiore, L., Jones, C., Cassirer, A., & Sifre, L. (2022). Improving language models by retrieving from trillions of tokens. In Proceedings of the 39th International Conference on Machine Learning (pp. 2206-2240). PMLR.
6. Asai, A., Wu, Z., Wang, Y., Sil, A., & Hajishirzi, H. (2024). Self-RAG: Learning to retrieve, generate, and critique through self-reflection. In The Twelfth International Conference on Learning Representations. ICLR.
7. Shi, W., Min, S., Yasunaga, M., Seo, M., James, R., Lewis, M., Zettlemoyer, L., & Yih, W. (2023). REPLUG: Retrieval-augmented black-box language models. arXiv preprint arXiv:2301.12652.
8. Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., & Wang, H. (2023). Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997.
9. Ram, O., Levine, Y., Dalmedigos, I., Muhlgay, D., Shashua, A., Leyton-Brown, K., & Shoham, Y. (2023). In-context retrieval-augmented language models. Transactions of the Association for Computational Linguistics, 11, 1316-1331.
10. Chen, D., Fisch, A., Weston, J., & Bordes, A. (2017). Reading Wikipedia to answer open-domain questions. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (pp. 1870-1879). Association for Computational Linguistics.
11. Petroni, F., Rocktäschel, T., Riedel, S., Lewis, P., Bakhtin, A., Wu, Y., & Miller, A. (2019). Language models as knowledge bases? In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (pp. 2463-2473). Association for Computational Linguistics.
12. Dhingra, B., Mazaitis, K., & Cohen, W. W. (2017). Quasar: Datasets for question answering by search and reading. arXiv preprint arXiv:1707.03904.
13. Zhu, Y., Kiros, R., Zemel, R., Salakhutdinov, R., Urtasun, R., Torralba, A., & Fidler, S. (2015). Aligning books and movies: Towards story-like visual explanations by watching movies and reading books. In Proceedings of the IEEE International Conference on Computer Vision (pp. 19-27). IEEE.
14. Thakur, N., Reimers, N., Rücklé, A., Srivastava, A., & Gurevych, I. (2021). BEIR: A heterogeneous benchmark for zero-shot evaluation of information retrieval models. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2). NeurIPS.
15. Chen, J., Xiao, S., Zhang, P., Luo, K., Lian, D., & Liu, K. (2024). M3-Embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. In Findings of the Association for Computational Linguistics: ACL 2024 (pp. 2318-2335). Association for Computational Linguistics.
16. Deng, Q., Liu, S., Qiu, H., Long, N., Lin, W., & Chen, S. (2026, April). Unified Semantic Space and Attention-Based Fusion Framework for Multi-Source Heterogeneous Retrieval-Augmented Generation. In 2026 6th International Conference on Artificial Intelligence and Industrial Technology Applications (AIITA) (pp. 591-597). IEEE.
17. Wang, L., Yang, N., Huang, X., Jiao, B., Yang, L., Jiang, D., Majumder, R., & Wei, F. (2022). Text embeddings by weakly-supervised contrastive pre-training. arXiv preprint arXiv:2212.03533.
18. Malkov, Y. A., & Yashunin, D. A. (2020). Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(4), 824-836.
19. Johnson, J., Douze, M., & Jégou, H. (2019). Billion-scale similarity search with GPUs. IEEE Transactions on Big Data, 7(3), 535-547.
20. Mitchell, M., Wu, S., Zaldivar, A., Barnes, P., Vasserman, L., Hutchinson, B., Spitzer, E., Raji, I. D., & Gebru, T. (2019). Model cards for model reporting. In Proceedings of the Conference on Fairness, Accountability, and Transparency (pp. 220-229). ACM.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Engineering Systems and Digital Innovation
This work is licensed under a Creative Commons Attribution 4.0 International License.
