{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T08:32:17Z","timestamp":1768293137258,"version":"3.49.0"},"reference-count":50,"publisher":"Association for Computing Machinery (ACM)","issue":"2","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["SIGKDD Explor. Newsl."],"published-print":{"date-parts":[[2025,12,30]]},"abstract":"<jats:p>Time Series Forecasting (TSF) has long been a challenge in time series analysis. Inspired by the success of Large Language Models (LLMs), researchers are now developing Large Time Series Models (LTSMs), universal transformerbased models that use autoregressive prediction to improve TSF. However, training LTSMs on heterogeneous time series data poses unique challenges, including diverse frequencies, dimensions, scalability, and patterns across datasets. Recent efforts have studied and evaluated various design choices aimed at enhancing LTSM training and generalization capabilities. Despite progress in both paradigms, there is no unified framework for systematically evaluating models and design choices across them. However, these design choices are typically studied and evaluated in isolation and are not compared collectively. In this work, we introduce LTSM-Bundle, a comprehensive toolbox and benchmark for training LTSMs, spanning pre-processing techniques, model configurations, and dataset configurations. We modularize and benchmark LTSMs across multiple dimensions, including prompting strategies, tokenization approaches, training paradigms, base model selection, data quantity, and dataset diversity. By combining the most effective design choices, the combination achieves state-of-the-art zero-shot and few-shot performance while providing a reproducible foundation for evaluating both traditional LSF models and emerging LTSMs. Our source code is available at https: \/\/github.com\/datamllab\/ltsm<\/jats:p>","DOI":"10.1145\/3787470.3787475","type":"journal-article","created":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:46:21Z","timestamp":1767228381000},"page":"43-61","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["LTSM-Bundle: A Toolbox and Benchmark on Large Language Models for Time Series Forecasting"],"prefix":"10.1145","volume":"27","author":[{"given":"Yu-Neng","family":"Chuang","sequence":"first","affiliation":[{"name":"Rice University"}]},{"given":"Songchen","family":"Li","sequence":"additional","affiliation":[{"name":"Rice University"}]},{"given":"Jiayi","family":"Yuan","sequence":"additional","affiliation":[{"name":"Rice University"}]},{"given":"Guanchu","family":"Wang","sequence":"additional","affiliation":[{"name":"University of North Carolina at Charlotte"}]},{"given":"Kwei-Herng","family":"Lai","sequence":"additional","affiliation":[{"name":"Rice University"}]},{"given":"Songyuan","family":"Sui","sequence":"additional","affiliation":[{"name":"Rice University"}]},{"given":"Leisheng","family":"Yu","sequence":"additional","affiliation":[{"name":"Rice University"}]},{"given":"Sirui","family":"Ding","sequence":"additional","affiliation":[{"name":"University of California, San Francisco"}]},{"given":"Chia-Yuan","family":"Chang","sequence":"additional","affiliation":[{"name":"Texas A&amp;M University"}]},{"given":"Alfredo","family":"Costilla Reyes","sequence":"additional","affiliation":[{"name":"Rice University"}]},{"given":"Daochen","family":"Zha","sequence":"additional","affiliation":[{"name":"Rice University"}]},{"given":"Xia","family":"Hu","sequence":"additional","affiliation":[{"name":"Rice University"}]}],"member":"320","published-online":{"date-parts":[[2025,12,31]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"et al. Chronos: Learning the language of time series. arXiv preprint arXiv:2403.07815","author":"Ansari A. F.","year":"2024","unstructured":"A. F. Ansari, L. Stella, C. Turkmen, X. Zhang, P. Mercado, H. Shen, O. Shchur, S. S. Rangapuram, S. P. Arango, S. Kapoor, et al. Chronos: Learning the language of time series. arXiv preprint arXiv:2403.07815, 2024."},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/UKSim.2014.67"},{"key":"e_1_2_1_3_1","volume-title":"Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification. the Journal of the Acoustical Society of America, 55(6):1304--1312","author":"Atal B. S.","year":"1974","unstructured":"B. S. Atal. Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification. the Journal of the Acoustical Society of America, 55(6):1304--1312, 1974."},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.softx.2020.100456"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589316"},{"key":"e_1_2_1_6_1","volume-title":"Llm4ts: Twostage fine-tuning for time-series forecasting with pretrained llms. arXiv preprint arXiv:2308.08469","author":"Chang C.","year":"2023","unstructured":"C. Chang, W.-C. Peng, and T.-F. Chen. Llm4ts: Twostage fine-tuning for time-series forecasting with pretrained llms. arXiv preprint arXiv:2308.08469, 2023."},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01205"},{"key":"e_1_2_1_8_1","volume-title":"A decoderonly foundation model for time-series forecasting. arXiv preprint arXiv:2310.10688","author":"Das A.","year":"2023","unstructured":"A. Das, W. Kong, R. Sen, and Y. Zhou. A decoderonly foundation model for time-series forecasting. arXiv preprint arXiv:2310.10688, 2023."},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"e_1_2_1_10_1","first-page":"36","article-title":"Forecastpfn: Synthetically-trained zeroshot forecasting","author":"Dooley S.","year":"2024","unstructured":"S. Dooley, G. S. Khurana, C. Mohapatra, S. V. Naidu, and C. White. Forecastpfn: Synthetically-trained zeroshot forecasting. Advances in Neural Information Processing Systems, 36, 2024.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_11_1","unstructured":"S. Elsworth and S. G\u00a8uttel. Time series forecasting using lstm networks: A symbolic approach. arXiv preprint arXiv:2003.05672 2020."},{"key":"e_1_2_1_12_1","first-page":"220","volume-title":"BIOSIGNALS","author":"Fernandes L.","year":"2020","unstructured":"L. Fernandes, M. Barandas, and H. Gamboa. Learning human behaviour patterns by trajectory and activity recognition. In BIOSIGNALS, pages 220--227, 2020."},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5220\/0005699601900197"},{"key":"e_1_2_1_14_1","volume-title":"Evaluating large language models on time series feature understanding: A comprehensive taxonomy and benchmark. arXiv preprint arXiv:2404.16563","author":"Fons E.","year":"2024","unstructured":"E. Fons, R. Kaur, S. Palande, Z. Zeng, T. Balch, M. Veloso, and S. Vyetrenko. Evaluating large language models on time series feature understanding: A comprehensive taxonomy and benchmark. arXiv preprint arXiv:2404.16563, 2024."},{"key":"e_1_2_1_15_1","first-page":"1189","volume-title":"Greedy function approximation: a gradient boosting machine. Annals of statistics","author":"Friedman J. H.","year":"2001","unstructured":"J. H. Friedman. Greedy function approximation: a gradient boosting machine. Annals of statistics, pages 1189--1232, 2001."},{"key":"e_1_2_1_16_1","volume-title":"Timegpt-1. arXiv preprint arXiv:2310.03589","author":"Garza A.","year":"2023","unstructured":"A. Garza and M. Mergenthaler-Canseco. Timegpt-1. arXiv preprint arXiv:2310.03589, 2023."},{"key":"e_1_2_1_17_1","first-page":"36","article-title":"Large language models are zero-shot time series forecasters","author":"Gruver N.","year":"2024","unstructured":"N. Gruver, M. Finzi, S. Qiu, and A. G. Wilson. Large language models are zero-shot time series forecasters. Advances in Neural Information Processing Systems, 36, 2024.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_18_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu E. J.","year":"2021","unstructured":"E. J. Hu, Y. Shen, P. Wallis, Z. Allen-Zhu, Y. Li, S. Wang, L. Wang, and W. Chen. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685, 2021."},{"key":"e_1_2_1_19_1","volume-title":"December","author":"Javaheripi M.","year":"2023","unstructured":"M. Javaheripi and S. Bubeck. Phi-2: The surprising power of small language models, December 2023."},{"key":"e_1_2_1_20_1","volume-title":"et al. Time-llm: Time series forecasting by reprogramming large language models. arXiv preprint arXiv:2310.01728","author":"Jin M.","year":"2023","unstructured":"M. Jin, S. Wang, L. Ma, Z. Chu, J. Y. Zhang, X. Shi, P.-Y. Chen, Y. Liang, Y.-F. Li, S. Pan, et al. Time-llm: Time series forecasting by reprogramming large language models. arXiv preprint arXiv:2310.01728, 2023."},{"key":"e_1_2_1_21_1","volume-title":"Reformer: The efficient transformer. arXiv preprint arXiv:2001.04451","author":"Kitaev N.","year":"2020","unstructured":"N. Kitaev, L. Kaiser, and A. Levskaya. Reformer: The efficient transformer. arXiv preprint arXiv:2001.04451, 2020."},{"key":"e_1_2_1_22_1","first-page":"80","volume-title":"2009 International Conference on Electrical and Electronics Engineering-ELECO","author":"Kocaman C\u00b8","year":"2009","unstructured":"C\u00b8 . Kocaman and M. \u00a8 Ozdemir. Comparison of statistical methods and wavelet energy coefficients for determining two common pq disturbances: Sag and swell. In 2009 International Conference on Electrical and Electronics Engineering-ELECO 2009, pages I--80. IEEE, 2009."},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210006"},{"key":"e_1_2_1_24_1","volume-title":"et al. Foundts: Comprehensive and unified benchmarking of foundation models for time series forecasting. arXiv preprint arXiv:2410.11802","author":"Li Z.","year":"2024","unstructured":"Z. Li, X. Qiu, P. Chen, Y. Wang, H. Cheng, Y. Shu, J. Hu, C. Guo, A. Zhou, Q. Wen, et al. Foundts: Comprehensive and unified benchmarking of foundation models for time series forecasting. arXiv preprint arXiv:2410.11802, 2024."},{"key":"e_1_2_1_25_1","first-page":"77888","article-title":"Time-mmd: Multi-domain multimodal dataset for time series analysis","volume":"37","author":"Liu H.","year":"2025","unstructured":"H. Liu, S. Xu, Z. Zhao, L. Kong, H. Prabhakar Kamarthi, A. Sasanur, M. Sharma, J. Cui, Q. Wen, C. Zhang, et al. Time-mmd: Multi-domain multimodal dataset for time series analysis. Advances in Neural Information Processing Systems, 37:77888--77933, 2025.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_26_1","first-page":"9881","article-title":"Non-stationary transformers: Exploring the stationarity in time series forecasting","volume":"35","author":"Liu Y.","year":"2022","unstructured":"Y. Liu, H. Wu, J. Wang, and M. Long. Non-stationary transformers: Exploring the stationarity in time series forecasting. Advances in Neural Information Processing Systems, 35:9881--9893, 2022.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_27_1","volume-title":"A cnn-- lstm model for gold price time-series forecasting. Neural computing and applications, 32:17351--17360","author":"Livieris I. E.","year":"2020","unstructured":"I. E. Livieris, E. Pintelas, and P. Pintelas. A cnn-- lstm model for gold price time-series forecasting. Neural computing and applications, 32:17351--17360, 2020."},{"key":"e_1_2_1_28_1","volume-title":"A time series is worth 64 words: Long-term forecasting with transformers. arXiv preprint arXiv:2211.14730","author":"Nie Y.","year":"2022","unstructured":"Y. Nie, N. H. Nguyen, P. Sinthong, and J. Kalagnanam. A time series is worth 64 words: Long-term forecasting with transformers. arXiv preprint arXiv:2211.14730, 2022."},{"key":"e_1_2_1_29_1","volume-title":"Guide to numpy","author":"Oliphant T. E.","year":"2006","unstructured":"T. E. Oliphant et al. Guide to numpy, volume 1. Trelgol Publishing USA, 2006."},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1243\/09544062JMES1224"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.3642604"},{"key":"e_1_2_1_32_1","volume-title":"et al. Easytime: Time series forecasting made easy. arXiv preprint arXiv:2412.17603","author":"Qiu X.","year":"2024","unstructured":"X. Qiu, X. Li, R. Pang, Z. Pan, X. Wu, L. Yang, J. Hu, Y. Shu, X. Lu, C. Yang, et al. Easytime: Time series forecasting made easy. arXiv preprint arXiv:2412.17603, 2024."},{"issue":"8","key":"e_1_2_1_33_1","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford A.","year":"2019","unstructured":"A. Radford, J. Wu, R. Child, D. Luan, D. Amodei, I. Sutskever, et al. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9, 2019.","journal-title":"OpenAI blog"},{"key":"e_1_2_1_34_1","volume-title":"Providing machine learning and data science utilities and extensions to pythons scientific computing stack. Journal of open source software, 3(24):638","author":"Raschka S.","year":"2018","unstructured":"S. Raschka. Mlxtend: Providing machine learning and data science utilities and extensions to pythons scientific computing stack. Journal of open source software, 3(24):638, 2018."},{"key":"e_1_2_1_35_1","volume-title":"Preprint","author":"Rasul K.","year":"2024","unstructured":"K. Rasul, A. Ashok, A. R. Williams, H. Ghonia, R. Bhagwatkar, A. Khorasani, M. J. D. Bayazi, G. Adamopoulos, R. Riachi, N. Hassen, et al. Lagllama: Towards foundation models for probabilistic time series forecasting. Preprint, 2024."},{"key":"e_1_2_1_36_1","volume-title":"Test: Text prototype aligned embedding to activate llm's ability for time series. arXiv preprint arXiv:2308.08241","author":"Sun C.","year":"2023","unstructured":"C. Sun, Y. Li, H. Li, and S. Hong. Test: Text prototype aligned embedding to activate llm's ability for time series. arXiv preprint arXiv:2308.08241, 2023."},{"key":"e_1_2_1_37_1","volume-title":"Are language models actually useful for time series forecasting? arXiv preprint arXiv:2406.16964","author":"Tan M.","year":"2024","unstructured":"M. Tan, M. A. Merrill, V. Gupta, T. Althoff, and T. Hartvigsen. Are language models actually useful for time series forecasting? arXiv preprint arXiv:2406.16964, 2024."},{"key":"e_1_2_1_38_1","unstructured":"H. U. Power spectrum and bandwidth. . 2003."},{"key":"e_1_2_1_39_1","volume-title":"Attention is all you need. Advances in neural information processing systems, 30","author":"Vaswani A.","year":"2017","unstructured":"A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin. Attention is all you need. Advances in neural information processing systems, 30, 2017."},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAU.1967.1161901"},{"key":"e_1_2_1_41_1","volume-title":"Unified training of universal time series forecasting transformers. arXiv preprint arXiv:2402.02592","author":"Woo G.","year":"2024","unstructured":"G. Woo, C. Liu, A. Kumar, C. Xiong, S. Savarese, and D. Sahoo. Unified training of universal time series forecasting transformers. arXiv preprint arXiv:2402.02592, 2024."},{"key":"e_1_2_1_42_1","volume-title":"Etsformer: Exponential smoothing transformers for timeseries forecasting. arXiv preprint arXiv:2202.01381","author":"Woo G.","year":"2022","unstructured":"G. Woo, C. Liu, D. Sahoo, A. Kumar, and S. Hoi. Etsformer: Exponential smoothing transformers for timeseries forecasting. arXiv preprint arXiv:2202.01381, 2022."},{"key":"e_1_2_1_43_1","volume-title":"The eleventh international conference on learning representations","author":"Wu H.","year":"2022","unstructured":"H. Wu, T. Hu, Y. Liu, H. Zhou, J. Wang, and M. Long. Timesnet: Temporal 2d-variation modeling for general time series analysis. In The eleventh international conference on learning representations, 2022."},{"key":"e_1_2_1_44_1","volume-title":"Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. Advances in neural information processing systems, 34:22419--22430","author":"Wu H.","year":"2021","unstructured":"H. Wu, J. Xu, J. Wang, and M. Long. Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. Advances in neural information processing systems, 34:22419--22430, 2021."},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsv.2005.06.005"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26317"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"e_1_2_1_48_1","first-page":"27268","volume-title":"International conference on machine learning","author":"Zhou T.","year":"2022","unstructured":"T. Zhou, Z. Ma, Q. Wen, X. Wang, L. Sun, and R. Jin. Fedformer: Frequency enhanced decomposed transformer for long-term series forecasting. In International conference on machine learning, pages 27268-- 27286. PMLR, 2022."},{"key":"e_1_2_1_49_1","volume-title":"One fits all: Power general time series analysis by pretrained lm. Advances in neural information processing systems, 36:43322--43355","author":"Zhou T.","year":"2023","unstructured":"T. Zhou, P. Niu, L. Sun, R. Jin, et al. One fits all: Power general time series analysis by pretrained lm. Advances in neural information processing systems, 36:43322--43355, 2023."},{"key":"e_1_2_1_50_1","volume-title":"CRC standard probability and statistics tables and formulae","author":"Zwillinger D.","year":"1999","unstructured":"D. Zwillinger and S. Kokoska. CRC standard probability and statistics tables and formulae. Crc Press, 1999."}],"container-title":["ACM SIGKDD Explorations Newsletter"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3787470.3787475","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T00:43:44Z","timestamp":1768265024000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3787470.3787475"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,30]]},"references-count":50,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,12,30]]}},"alternative-id":["10.1145\/3787470.3787475"],"URL":"https:\/\/doi.org\/10.1145\/3787470.3787475","relation":{},"ISSN":["1931-0145","1931-0153"],"issn-type":[{"value":"1931-0145","type":"print"},{"value":"1931-0153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,30]]},"assertion":[{"value":"2025-12-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}