{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T20:21:58Z","timestamp":1777062118767,"version":"3.51.4"},"reference-count":37,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2025,4,17]],"date-time":"2025-04-17T00:00:00Z","timestamp":1744848000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Energy R&amp;D Center of Petroleum Refining Technology (RIPP, SINOPEC)","award":["36800000-23-ZC0607-0107"],"award-info":[{"award-number":["36800000-23-ZC0607-0107"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>Large language models (LLMs) have recently demonstrated notable performance, particularly in addressing the challenge of extensive data requirements when training traditional forecasting models. However, these methods encounter significant challenges when applied to high-dimensional and domain-specific datasets. These challenges primarily arise from inability to effectively model inter-variable dependencies and capture variable-specific characteristics, leading to suboptimal performance in complex forecasting scenarios. To address these limitations, we propose ADTime, an adaptive LLM-based approach for multivariate time series forecasting. ADTime employs advanced preprocessing techniques to identify latent relationships among key variables and temporal features. Additionally, it integrates temporal alignment mechanisms and prompt-based strategies to enhance the semantic understanding of forecasting tasks by LLMs. Experimental results show that ADTime outperforms state-of-the-art methods, reducing MSE by 9.5% and MAE by 6.1% on public datasets, and by 17.1% and 13.5% on domain-specific datasets. Furthermore, zero-shot experiments on real-world refinery datasets demonstrate that ADTime exhibits stronger generalization capabilities across various transfer scenarios. These findings highlight the potential of ADTime in advancing complex, domain-specific time series forecasting tasks.<\/jats:p>","DOI":"10.3390\/make7020035","type":"journal-article","created":{"date-parts":[[2025,4,17]],"date-time":"2025-04-17T06:53:46Z","timestamp":1744872826000},"page":"35","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["ADTime: Adaptive Multivariate Time Series Forecasting Using LLMs"],"prefix":"10.3390","volume":"7","author":[{"given":"Jinglei","family":"Pei","sequence":"first","affiliation":[{"name":"Institute of Computing Technology, University of Chinese Academy of Sciences, Beijing 100190, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Research Institute of Petroleum Processing, SINOPEC, Beijing 100083, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9305-9439","authenticated-orcid":false,"given":"Ting","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, University of Chinese Academy of Sciences, Beijing 100190, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingbin","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, University of Chinese Academy of Sciences, Beijing 100190, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinghua","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, University of Chinese Academy of Sciences, Beijing 100190, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kang","family":"Qin","sequence":"additional","affiliation":[{"name":"Research Institute of Petroleum Processing, SINOPEC, Beijing 100083, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,4,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1038\/s41597-020-0548-x","article-title":"Multivariate time series dataset for space weather data analytics","volume":"7","author":"Angryk","year":"2020","journal-title":"Sci. Data"},{"key":"ref_2","first-page":"36314","article-title":"Medformer: A Multi-Granularity Patching Transformer for Medical Time-Series Classification","volume":"37","author":"Wang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"3430","DOI":"10.1109\/TITS.2015.2457240","article-title":"Trend modeling for traffic time series analysis: An integrated study","volume":"16","author":"Li","year":"2015","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_4","first-page":"377","article-title":"Energy forecasting with robust, flexible, and explainable machine learning algorithms","volume":"44","author":"Zhu","year":"2023","journal-title":"AI Mag."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Yu, X., Chen, Z., Ling, Y., Dong, S., Liu, Z., and Lu, Y. (2023). Temporal Data Meets LLM\u2013Explainable Financial Time Series Forecasting. arXiv.","DOI":"10.18653\/v1\/2023.emnlp-industry.69"},{"key":"ref_6","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_7","unstructured":"Liu, T., and Low, B.K.H. (2023). Goat: Fine-tuned llama outperforms gpt-4 on arithmetic tasks. arXiv."},{"key":"ref_8","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.A., Lacroix, T., Rozi\u00e8re, B., Goyal, N., Hambro, E., and Azhar, F. (2023). Llama: Open and efficient foundation language models. arXiv."},{"key":"ref_9","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref_10","unstructured":"Nie, Y., Nguyen, N.H., Sinthong, P., and Kalagnanam, J. (2023, January 1\u20135). A Time Series is Worth 64 Words: Long-term Forecasting with Transformers. Proceedings of the Eleventh International Conference on Learning Representations, Kigali, Rwanda."},{"key":"ref_11","first-page":"11121","article-title":"Are transformers effective for time series forecasting?","volume":"37","author":"Zeng","year":"2023","journal-title":"AAAI Conf. Artif. Intell."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Wen, Q., Zhou, T., Zhang, C., Chen, W., Ma, Z., Yan, J., and Sun, L. (2023, January 19\u201325). Transformers in time series: A survey. Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, Macao, China.","DOI":"10.24963\/ijcai.2023\/759"},{"key":"ref_13","first-page":"9881","article-title":"Non-stationary transformers: Exploring the stationarity in time series forecasting","volume":"35","author":"Liu","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_14","unstructured":"Kitaev, N., Kaiser, \u0141., and Levskaya, A. (2020, January 30). Reformer: The efficient transformer. Proceedings of the International Conference on Learning Representations, Addis Ababa, Ethiopia."},{"key":"ref_15","unstructured":"Liu, Y., Hu, T., Zhang, H., Wu, H., Wang, S., Ma, L., and Long, M. (2023, January 7\u201311). itransformer: Inverted transformers are effective for time series forecasting. Proceedings of the Twelfth International Conference on Learning Representations, Vienna, Austria."},{"key":"ref_16","first-page":"11106","article-title":"Informer: Beyond efficient transformer for long sequence time-series forecasting","volume":"35","author":"Zhou","year":"2021","journal-title":"AAAI Conf. Artif. Intell."},{"key":"ref_17","first-page":"22419","article-title":"Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting","volume":"34","author":"Wu","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_18","unstructured":"Zhou, T., Ma, Z., Wen, Q., Wang, X., Sun, L., and Jin, R. (2022, January 17\u201323). Fedformer: Frequency enhanced decomposed transformer for long-term series forecasting. Proceedings of the International conference on machine learning. PMLR, Baltimore, MD, USA."},{"key":"ref_19","unstructured":"Chen, P., Zhang, Y., Cheng, Y., Shu, Y., Wang, Y., Wen, Q., Yang, B., and Guo, C. (2024). Pathformer: Multi-scale transformers with adaptive pathways for time series forecasting. arXiv."},{"key":"ref_20","unstructured":"Jin, M., Zhang, Y., Chen, W., Zhang, K., Liang, Y., Yang, B., Wang, J., Pan, S., and Wen, Q. (2024, January 21\u201327). Position: What Can Large Language Models Tell Us about Time Series Analysis. Proceedings of the Forty-first International Conference on Machine Learning, Vienna, Austria."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Liu, C., Yang, S., Xu, Q., Li, Z., Long, C., Li, Z., and Zhao, R. (2024, January 24\u201327). Spatial-temporal large language model for traffic prediction. Proceedings of the 2024 25th IEEE International Conference on Mobile Data Management (MDM), Brussels, Belgium.","DOI":"10.1109\/MDM61037.2024.00025"},{"key":"ref_22","first-page":"43322","article-title":"One fits all: Power general time series analysis by pretrained lm","volume":"36","author":"Zhou","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Liu, C., Xu, Q., Miao, H., Yang, S., Zhang, L., Long, C., Li, Z., and Zhao, R. (2025, January 20\u201322). TimeCMA: Towards LLM-Empowered Time Series Forecasting via Cross-Modality Alignment. Proceedings of the AAAI, Dubai, United Arab Emirates.","DOI":"10.1609\/aaai.v39i18.34067"},{"key":"ref_24","unstructured":"Sun, C., Li, H., Li, Y., and Hong, S. (2024, January 7\u201311). TEST: Text prototype aligned embedding to activate LLM\u2019s ability for time series. Proceedings of the Twelfth International Conference on Learning Representations, Vienna, Austria."},{"key":"ref_25","unstructured":"Jin, M., Wang, S., Ma, L., Chu, Z., Zhang, J.Y., Shi, X., Chen, P.Y., Liang, Y., Li, Y.F., and Pan, S. (2024, January 7\u201311). Time-llm: Time series forecasting by reprogramming large language models. Proceedings of the Twelfth International Conference on Learning Representations, Vienna, Austria."},{"key":"ref_26","unstructured":"Cao, D., Jia, F., Arik, S.O., Pfister, T., Zheng, Y., Ye, W., and Liu, Y. (2024, January 7\u201311). Tempo: Prompt-based generative pre-trained transformer for time series forecasting. Proceedings of the Twelfth International Conference on Learning Representations, Vienna, Austria."},{"key":"ref_27","unstructured":"Wang, S., Wu, H., Shi, X., Hu, T., Luo, H., Ma, L., Zhang, J.Y., and Zhou, J. (2024, January 7\u201311). Timemixer: Decomposable multiscale mixing for time series forecasting. Proceedings of the Twelfth International Conference on Learning Representations, Vienna, Austria."},{"key":"ref_28","first-page":"3","article-title":"STL: A seasonal-trend decomposition","volume":"6","author":"Cleveland","year":"1990","journal-title":"J. Off. Stat."},{"key":"ref_29","unstructured":"Oreshkin, B.N., Carpov, D., Chapados, N., and Bengio, Y. (2019, January 6\u20139). N-BEATS: Neural basis expansion analysis for interpretable time series forecasting. Proceedings of the International Conference on Learning Representations, New Orleans, LA, USA."},{"key":"ref_30","unstructured":"Wu, H., Hu, T., Liu, Y., Zhou, H., Wang, J., and Long, M. (2023, January 1\u20135). Timesnet: Temporal 2d-variation modeling for general time series analysis. Proceedings of the Eleventh International Conference on Learning Representations, Kigali, Rwanda."},{"key":"ref_31","unstructured":"Liu, S., Yu, H., Liao, C., Li, J., Lin, W., Liu, A.X., and Dustdar, S. (2022, January 25\u201329). Pyraformer: Low-complexity pyramidal attention for long-range time series modeling and forecasting. Proceedings of the International Conference on Learning Representations, Virtual."},{"key":"ref_32","unstructured":"Zhang, Y., and Yan, J. (2023, January 1\u20135). Crossformer: Transformer utilizing cross-dimension dependency for multivariate time series forecasting. Proceedings of the Eleventh International Conference on Learning Representations, Kigali, Rwanda."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"7129","DOI":"10.1109\/TKDE.2024.3400008","article-title":"The capacity and robustness trade-off: Revisiting the channel independent strategy for multivariate time series forecasting","volume":"36","author":"Han","year":"2024","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_34","unstructured":"Wang, X., Zhou, T., Wen, Q., Gao, J., Ding, B., and Jin, R. (2024, January 7\u201311). CARD: Channel aligned robust blend transformer for time series forecasting. Proceedings of the Twelfth International Conference on Learning Representations, Vienna, Austria."},{"key":"ref_35","unstructured":"Chen, J., Lenssen, J.E., Feng, A., Hu, W., Fey, M., Tassiulas, L., Leskovec, J., and Ying, R. (2024). From Similarity to Superiority: Channel Clustering for Time Series Forecasting. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Li, X.L., and Liang, P. (2021). Prefix-tuning: Optimizing continuous prompts for generation. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Association for Computational Linguistics. Volume 1: Long Papers.","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref_37","first-page":"861","article-title":"Large language models are zero-shot time series forecasters","volume":"36","author":"Gruver","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/2\/35\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:16:23Z","timestamp":1760030183000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/2\/35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,17]]},"references-count":37,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["make7020035"],"URL":"https:\/\/doi.org\/10.3390\/make7020035","relation":{},"ISSN":["2504-4990"],"issn-type":[{"value":"2504-4990","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,17]]}}}