---
title: "Large Language Models Are Zero-Shot Time Series Forecasters"
description: "Gruver, Finzi, Qiu and Wilson propose LLMTime, which writes numerical sequences as digit strings… 57 references, cited by 76 papers here."
authors: ["Nate Gruver", "Marc Finzi", "Shikai Qiu", "Andrew Gordon Wilson"]
year: 2023
venue: "arXiv:2310.07820"
source: "https://arxiv.org/abs/2310.07820"
doi: "10.48550/arxiv.2310.07820"
arxiv: "2310.07820"
licence: "arXiv — non-exclusive license to distribute"
licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/gruver-2023-large-language-models-zero-shot/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/gruver-2023-large-language-models-zero-shot/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2023](https://md.research.elamur.ai/free/en/papers/2023/page/3/) / Large Language Models Are Zero-Shot Time Series Forecasters

# Large Language Models Are Zero-Shot Time Series Forecasters

**Authors:** Nate Gruver, Marc Finzi, Shikai Qiu and [Andrew Gordon Wilson](https://md.research.elamur.ai/free/en/authors/andrew-gordon-wilson/) · **Year:** 2023 · **Venue:** [arXiv:2310.07820](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/) ([NeurIPS 2023](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2023/)) · **Licence:** [arXiv — non-exclusive license to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2310.07820) · [PDF](https://arxiv.org/pdf/2310.07820) · [DOI 10.48550/arxiv.2310.07820](https://doi.org/10.48550/arxiv.2310.07820) · [arXiv 2310.07820](https://arxiv.org/abs/2310.07820) · [OpenAlex](https://openalex.org/W7133223873)

**Citations:** 192 citations (OpenAlex, 2026-10-14) · [76](https://md.research.elamur.ai/free/en/papers/gruver-2023-large-language-models-zero-shot/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Time series forecasting has lacked large-scale pretraining. Data come from very different sources and scales, values are often missing, and no standard self-supervised objective exists. As a result, simple methods such as ARIMA frequently beat deep networks. Gruver, Finzi, Qiu and Wilson propose LLMTime, which writes numerical sequences as digit strings and lets a pretrained language model such as GPT-3 or LLaMA-2 continue them. Sampled continuations serve as probabilistic forecasts. No fine-tuning on the target data is needed.

The method depends on two things. Values must be formatted to suit each model's tokenizer. The model's discrete token probabilities are also converted into continuous densities, which allows likelihood-based comparison. Without any task-specific training, LLMTime matches or outperforms dedicated forecasters. The authors attribute this to the model's capacity for multimodal distributions and its built-in preference for simple, repeating patterns such as seasonality. Accuracy generally grows with model size, but RLHF-aligned GPT-4 does worse than GPT-3. This makes forecasting accessible without domain expertise, heavy compute or large training sets.

## Key points
- **Tokenization matters:**
  - GPT-3's BPE tokenizer splits 42,235,630 into [422, 35, 630]. Inserting spaces between digits yields one token per digit and much better forecasts, as shown on the Australian Wine dataset from Darts.
  - LLaMA-2 already tokenizes digits individually, so extra spaces hurt its results.
- **Evaluation:** forecasts are scored with CRPS and with likelihoods, rather than MAE alone. Baselines include ARIMA, TCN and N-HiTS.
- **Missing values:** gaps can be written as "NaN" instead of being imputed. LLaMA-2 70B degrades less than interpolation-based baselines and remains competitive on CRPS.
- **Text abilities:** using chain-of-thought prompting, GPT-4 identified which synthetic function generated a series well above chance. It can also take textual side information as input.
- **GPT-4 caveat:** its weaker results stem from its number tokenization and poorer uncertainty calibration, likely caused by alignment. The work appeared at NeurIPS 2023, and code is available at github.com/ngruver/llmtime.

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

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🎯 Decision Sciences](https://md.research.elamur.ai/free/en/shelves/decision-sciences/) · 249 works · [🔊 Signal Processing](https://md.research.elamur.ai/free/en/shelves/computer-science/signal-processing/) · 493 works · [🎯 Management Science and Operations Research](https://md.research.elamur.ai/free/en/shelves/decision-sciences/management-science-and-operations-research/) · 134 works

🧭 Topics (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,894 works

## Cite

Cite as: Nate Gruver, Marc Finzi, Shikai Qiu and Andrew Gordon Wilson. 2023. Large Language Models Are Zero-Shot Time Series Forecasters. arXiv:2310.07820.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{gruver2023large,
  title = {{Large Language Models Are Zero-Shot Time Series Forecasters}},
  author = {Nate Gruver, Marc Finzi, Shikai Qiu and Andrew Gordon Wilson},
  year = {2023},
  doi = {10.48550/arxiv.2310.07820},
  eprint = {2310.07820},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2310.07820}
}
```

- [← previous GraphGPT: Graph Instruction Tuning for Large Language Models](https://md.research.elamur.ai/free/en/papers/tang-2023-graphgpt-graph-instruction-tuning-large/)
- [next → LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models](https://md.research.elamur.ai/free/en/papers/chen-2023-longlora-efficient-fine-tuning-long/)
- [↑ back to papers of 2023](https://md.research.elamur.ai/free/en/papers/2023/page/3/)

## References

57 references, 20 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Joshua Ainslie, Tao Lei, Michiel de Jong, Santiago Ontañón, Siddhartha Brahma, Yury Zemlyanskiy, David Uthus, Mandy Guo, James Lee-Thorp, Yi Tay, et al. [Colt5: Faster long-range transformers with conditional computation](https://md.research.elamur.ai/free/en/papers/ainslie-2023-colt5-faster-long-range-transformers/). arXiv preprint arXiv:2303.09752, 2023.
2. Zeyuan Allen-Zhu and Yuanzhi Li. Physics of language models: Part 1, context-free grammar. arXiv preprint arXiv:2305.13673, 2023. [find](https://scholar.google.com/scholar?q=Zeyuan+Allen%2DZhu+and+Yuanzhi+Li%2E+Physics+of+language+models%3A+Part+1%2C+context%2Dfree+grammar%2E+arXiv+preprint+arXiv%3A2305%2E13673%2C+2023%2E)
3. Cem Anil, Ashwini Pokle, Kaiqu Liang, Johannes Treutlein, Yuhuai Wu, Shaojie Bai, J Zico Kolter, and Roger B Grosse. Path independent equilibrium models can better exploit test-time computation. Advances in Neural Information Processing Systems, 35:7796–7809, 2022. [find](https://scholar.google.com/scholar?q=Cem+Anil%2C+Ashwini+Pokle%2C+Kaiqu+Liang%2C+Johannes+Treutlein%2C+Yuhuai+Wu%2C+Shaojie+Bai%2C+J+Zico+Kolter%2C+and+Roger+B+Grosse%2E+Path+independent+equilibrium+models+can+better+exploit+test%2Dtime+computation%2E+Advan)
4. Rohan Anil, Andrew M Dai, Orhan Firat, Melvin Johnson, Dmitry Lepikhin, Alexandre Passos, Siamak Shakeri, Emanuel Taropa, Paige Bailey, Zhifeng Chen, et al. [Palm 2 technical report](https://md.research.elamur.ai/free/en/papers/anil-2023-palm-2-technical-report/). arXiv preprint arXiv:2305.10403, 2023.
5. Anthropic. Introducing 100k context windows. Anthropic blog, 2023. URL [https://www.anthropic.com/index/100k-context-windows](https://www.anthropic.com/index/100k-context-windows). [↗](https://www.anthropic.com/index/100k-context-windows)
6. Gregory Benton, Nate Gruver, Wesley Maddox, and Andrew Gordon Wilson. Deep probabilistic time series forecasting over long horizons. openreview preprint, 2022. URL [https://openreview.net/forum?id=22h1XSEiN0](https://openreview.net/forum?id=22h1XSEiN0). [↗](https://openreview.net/forum?id=22h1XSEiN0)
7. Stella Biderman, USVSN Sai Prashanth, Lintang Sutawika, Hailey Schoelkopf, Quentin Anthony, Shivanshu Purohit, and Edward Raf. [Emergent and predictable memorization in large language models](https://md.research.elamur.ai/free/en/papers/biderman-2023-emergent-predictable-memorization-large-language/). arXiv preprint arXiv:2304.11158, 2023.
8. George EP Box and Gwilym M Jenkins. Some recent advances in forecasting and control. Journal of the Royal Statistical Society. Series C (Applied Statistics), 17(2):91–109, 1968. [find](https://scholar.google.com/scholar?q=George+EP+Box+and+Gwilym+M+Jenkins%2E+Some+recent+advances+in+forecasting+and+control%2E+Journal+of+the+Royal+Statistical+Society%2E+Series+C+%28Applied+Statistics%29%2C+17%282%29%3A91%E2%80%93109%2C+1968%2E)
9. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. [Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). Advances in neural information processing systems, 33:1877–1901, 2020.
10. Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin Tat Lee, Yuanzhi Li, Scott Lundberg, et al. [Sparks of artificial general intelligence: Early experiments with gpt-4](https://md.research.elamur.ai/free/en/papers/bubeck-2023-sparks-artificial-general-intelligence-early/). arXiv preprint arXiv:2303.12712, 2023.
11. Cristian Challu, Kin G Olivares, Boris N Oreshkin, Federico Garza, Max Mergenthaler, and Artur Dubrawski. N-hits: Neural hierarchical interpolation for time series forecasting. arXiv preprint arXiv:2201.12886, 2022. [find](https://scholar.google.com/scholar?q=Cristian+Challu%2C+Kin+G+Olivares%2C+Boris+N+Oreshkin%2C+Federico+Garza%2C+Max+Mergenthaler%2C+and+Artur+Dubrawski%2E+N%2Dhits%3A+Neural+hierarchical+interpolation+for+time+series+forecasting%2E+arXiv+preprint+arXiv%3A22)
12. Kent K Chang, Mackenzie Cramer, Sandeep Soni, and David Bamman. [Speak, memory: An archaeology of books known to chatgpt/gpt-4](https://md.research.elamur.ai/free/en/papers/chang-2023-speak-memory-archaeology-books-known/). arXiv preprint arXiv:2305.00118, 2023.
13. Paul F Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei. Deep reinforcement learning from human preferences. Advances in neural information processing systems, 30, 2017. [find](https://scholar.google.com/scholar?q=Paul+F+Christiano%2C+Jan+Leike%2C+Tom+Brown%2C+Miljan+Martic%2C+Shane+Legg%2C+and+Dario+Amodei%2E+Deep+reinforcement+learning+from+human+preferences%2E+Advances+in+neural+information+processing+systems%2C+30%2C+2017%2E)
14. Miles Cranmer. Interpretable machine learning for science with pysr and symbolicregression. jl. arXiv preprint arXiv:2305.01582, 2023. [find](https://scholar.google.com/scholar?q=Miles+Cranmer%2E+Interpretable+machine+learning+for+science+with+pysr+and+symbolicregression%2E+jl%2E+arXiv+preprint+arXiv%3A2305%2E01582%2C+2023%2E)
15. Grégoire Delétang, Anian Ruoss, Paul-Ambroise Duquenne, Elliot Catt, Tim Genewein, Christopher Mattern, Jordi Grau-Moya, Li Kevin Wenliang, Matthew Aitchison, Laurent Orseau, et al. [Language modeling is compression](https://md.research.elamur.ai/free/en/papers/deletang-2023-language-modeling-compression/). arXiv preprint arXiv:2309.10668, 2023.
16. Dazhao Du, Bing Su, and Zhewei Wei. Preformer: Predictive transformer with multi-scale segment-wise correlations for long-term time series forecasting. arXiv preprint arXiv:2202.11356, 2022. — [arXiv:2202.11356](https://arxiv.org/abs/2202.11356) [find](https://scholar.google.com/scholar?q=Dazhao+Du%2C+Bing+Su%2C+and+Zhewei+Wei%2E+Preformer%3A+Predictive+transformer+with+multi%2Dscale+segment%2Dwise+correlations+for+long%2Dterm+time+series+forecasting%2E+arXiv+preprint+arXiv%3A2202%2E11356%2C+2022%2E+%E2%80%94+%5BarXiv%3A)
17. Jacob R Gardner, Geoff Pleiss, David Bindel, Kilian Q Weinberger, and Andrew Gordon Wilson. Gpytorch: Blackbox matrix-matrix gaussian process inference with gpu acceleration. In Advances in Neural Information Processing Systems, 2018. [find](https://scholar.google.com/scholar?q=Jacob+R+Gardner%2C+Geoff+Pleiss%2C+David+Bindel%2C+Kilian+Q+Weinberger%2C+and+Andrew+Gordon+Wilson%2E+Gpytorch%3A+Blackbox+matrix%2Dmatrix+gaussian+process+inference+with+gpu+acceleration%2E+In+Advances+in+Neural+Inf)
18. Federico Garza, Max Mergenthaler Canseco, Cristian Challú, and Kin G Olivares. Statsforecast: Lightning fast forecasting with statistical and econometric models. PyCon: Salt Lake City, UT, USA, 2022. URL [https://github.com/Nixtla/statsforecast](https://github.com/Nixtla/statsforecast). [↗](https://github.com/Nixtla/statsforecast)
19. Rakshitha Godahewa, Christoph Bergmeir, Geoffrey I Webb, Rob J Hyndman, and Pablo Montero-Manso. Monash time series forecasting archive. arXiv preprint arXiv:2105.06643, 2021. — [arXiv:2105.06643](https://arxiv.org/abs/2105.06643) [find](https://scholar.google.com/scholar?q=Rakshitha+Godahewa%2C+Christoph+Bergmeir%2C+Geoffrey+I+Webb%2C+Rob+J+Hyndman%2C+and+Pablo+Montero%2DManso%2E+Monash+time+series+forecasting+archive%2E+arXiv+preprint+arXiv%3A2105%2E06643%2C+2021%2E+%E2%80%94+%5BarXiv%3A2105%2E06643%5D%28htt)
20. Micah Goldblum, Marc Finzi, Keefer Rowan, and Andrew Gordon Wilson. The no free lunch theorem, kolmogorov complexity, and the role of inductive biases in machine learning. arXiv preprint arXiv:2304.05366, 2023. — [arXiv:2304.05366](https://arxiv.org/abs/2304.05366) [find](https://scholar.google.com/scholar?q=Micah+Goldblum%2C+Marc+Finzi%2C+Keefer+Rowan%2C+and+Andrew+Gordon+Wilson%2E+The+no+free+lunch+theorem%2C+kolmogorov+complexity%2C+and+the+role+of+inductive+biases+in+machine+learning%2E+arXiv+preprint+arXiv%3A2304%2E05)
21. Ian Goodfellow, Yoshua Bengio, and Aaron Courville. Deep learning. MIT press, 2016. [find](https://scholar.google.com/scholar?q=Ian+Goodfellow%2C+Yoshua+Bengio%2C+and+Aaron+Courville%2E+Deep+learning%2E+MIT+press%2C+2016%2E)
22. Nate Gruver, Marc Finzi, Micah Goldblum, and Andrew Gordon Wilson. The lie derivative for measuring learned equivariance. arXiv preprint arXiv:2210.02984, 2022. — [arXiv:2210.02984](https://arxiv.org/abs/2210.02984) [find](https://scholar.google.com/scholar?q=Nate+Gruver%2C+Marc+Finzi%2C+Micah+Goldblum%2C+and+Andrew+Gordon+Wilson%2E+The+lie+derivative+for+measuring+learned+equivariance%2E+arXiv+preprint+arXiv%3A2210%2E02984%2C+2022%2E+%E2%80%94+%5BarXiv%3A2210%2E02984%5D%28https%3A%2F%2Farxiv%2Eorg%2F)
23. Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. [Measuring massive multitask language understanding](https://md.research.elamur.ai/free/en/papers/hendrycks-2020-measuring-massive-multitask-language-understanding/). arXiv preprint arXiv:2009.03300, 2020.
24. Julien Herzen, Francesco Lässig, Samuele Giuliano Piazzetta, Thomas Neuer, Léo Tafti, Guillaume Raille, Tomas Van Pottelbergh, Marek Pasieka, Andrzej Skrodzki, Nicolas Huguenin, et al. Darts: User-friendly modern machine learning for time series. The Journal of Machine Learning Research, 23(1):5442–… [find](https://scholar.google.com/scholar?q=Julien+Herzen%2C+Francesco+L%C3%A4ssig%2C+Samuele+Giuliano+Piazzetta%2C+Thomas+Neuer%2C+L%C3%A9o+Tafti%2C+Guillaume+Raille%2C+Tomas+Van+Pottelbergh%2C+Marek+Pasieka%2C+Andrzej+Skrodzki%2C+Nicolas+Huguenin%2C+et+al%2E+Darts%3A+User%2Dfri)
25. Hansika Hewamalage, Klaus Ackermann, and Christoph Bergmeir. Forecast evaluation for data scientists: common pitfalls and best practices. Data Mining and Knowledge Discovery, 37(2): 788–832, 2023. [find](https://scholar.google.com/scholar?q=Hansika+Hewamalage%2C+Klaus+Ackermann%2C+and+Christoph+Bergmeir%2E+Forecast+evaluation+for+data+scientists%3A+common+pitfalls+and+best+practices%2E+Data+Mining+and+Knowledge+Discovery%2C+37%282%29%3A+788%E2%80%93832%2C+2023%2E)
26. Ari Holtzman, Jan Buys, Li Du, Maxwell Forbes, and Yejin Choi. [The curious case of neural text degeneration](https://md.research.elamur.ai/free/en/papers/holtzman-2019-curious-case-neural-text-degeneration/). arXiv preprint arXiv:1904.09751, 2019.
27. Rob J Hyndman, Anne B Koehler, J Keith Ord, and Ralph D Snyder. Forecasting with exponential smoothing: the state space approach. Springer Science & Business Media, 2008. [find](https://scholar.google.com/scholar?q=Rob+J+Hyndman%2C+Anne+B+Koehler%2C+J+Keith+Ord%2C+and+Ralph+D+Snyder%2E+Forecasting+with+exponential+smoothing%3A+the+state+space+approach%2E+Springer+Science+%26+Business+Media%2C+2008%2E)
28. Shruti Kaushik, Abhinav Choudhury, Pankaj Kumar Sheron, Nataraj Dasgupta, Sayee Natarajan, Larry A Pickett, and Varun Dutt. Ai in healthcare: time-series forecasting using statistical, neural, and ensemble architectures. Frontiers in big data, 3:4, 2020. [find](https://scholar.google.com/scholar?q=Shruti+Kaushik%2C+Abhinav+Choudhury%2C+Pankaj+Kumar+Sheron%2C+Nataraj+Dasgupta%2C+Sayee+Natarajan%2C+Larry+A+Pickett%2C+and+Varun+Dutt%2E+Ai+in+healthcare%3A+time%2Dseries+forecasting+using+statistical%2C+neural%2C+and+ens)
29. Colin Lea, Rene Vidal, Austin Reiter, and Gregory D Hager. Temporal convolutional networks: A unified approach to action segmentation. In Computer Vision–ECCV 2016 Workshops: Amsterdam, The Netherlands, October 8-10 and 15-16, 2016, Proceedings, Part III 14, pages 47–54. Springer, 2016. [find](https://scholar.google.com/scholar?q=Colin+Lea%2C+Rene+Vidal%2C+Austin+Reiter%2C+and+Gregory+D+Hager%2E+Temporal+convolutional+networks%3A+A+unified+approach+to+action+segmentation%2E+In+Computer+Vision%E2%80%93ECCV+2016+Workshops%3A+Amsterdam%2C+The+Netherland)
30. Katherine Lee, Daphne Ippolito, Andrew Nystrom, Chiyuan Zhang, Douglas Eck, Chris Callison-Burch, and Nicholas Carlini. Deduplicating training data makes language models better. arXiv preprint arXiv:2107.06499, 2021. [find](https://scholar.google.com/scholar?q=Katherine+Lee%2C+Daphne+Ippolito%2C+Andrew+Nystrom%2C+Chiyuan+Zhang%2C+Douglas+Eck%2C+Chris+Callison%2DBurch%2C+and+Nicholas+Carlini%2E+Deduplicating+training+data+makes+language+models+better%2E+arXiv+preprint+arXiv%3A2)
31. Tiedong Liu and Bryan Kian Hsiang Low. [Goat: Fine-tuned llama outperforms gpt-4 on arithmetic tasks](https://md.research.elamur.ai/free/en/papers/liu-2023-goat-fine-tuned-llama-outperforms/). arXiv preprint arXiv:2305.14201, 2023.
32. Andriy Mnih and Geoffrey E Hinton. A scalable hierarchical distributed language model. Advances in neural information processing systems, 21, 2008. [find](https://scholar.google.com/scholar?q=Andriy+Mnih+and+Geoffrey+E+Hinton%2E+A+scalable+hierarchical+distributed+language+model%2E+Advances+in+neural+information+processing+systems%2C+21%2C+2008%2E)
33. Steffen Moritz and Thomas Bartz-Beielstein. imputets: time series missing value imputation in r. R J., 9(1):207, 2017. [find](https://scholar.google.com/scholar?q=Steffen+Moritz+and+Thomas+Bartz%2DBeielstein%2E+imputets%3A+time+series+missing+value+imputation+in+r%2E+R+J%2E%2C+9%281%29%3A207%2C+2017%2E)
34. Maxwell Nye, Anders Johan Andreassen, Guy Gur-Ari, Henryk Michalewski, Jacob Austin, David Bieber, David Dohan, Aitor Lewkowycz, Maarten Bosma, David Luan, et al. [Show your work: Scratchpads for intermediate computation with language models](https://md.research.elamur.ai/free/en/papers/al-2021-show-your-work-scratchpads-intermediate/). arXiv preprint arXiv:2112.00114, 2021.
35. Catherine Olsson, Nelson Elhage, Neel Nanda, Nicholas Joseph, Nova DasSarma, Tom Henighan, Ben Mann, Amanda Askell, Yuntao Bai, Anna Chen, Tom Conerly, Dawn Drain, Deep Ganguli, Zac Hatfield-Dodds, Danny Hernandez, Scott Johnston, Andy Jones, Jackson Kernion, Liane Lovitt, Kamal Ndousse, Dario Amode… — [In-context Learning and Induction Heads](https://md.research.elamur.ai/free/en/papers/olsson-2022-context-learning-induction-heads/)
36. Aaron van den Oord, Sander Dieleman, Heiga Zen, Karen Simonyan, Oriol Vinyals, Alex Graves, Nal Kalchbrenner, Andrew Senior, and Koray Kavukcuoglu. [Wavenet: A generative model for raw audio](https://md.research.elamur.ai/free/en/papers/oord-2016-wavenet-generative-model-raw-audio/). In 9th ISCA Speech Synthesis Workshop, pages 125–125. ISCA, 2016.
37. OpenAI. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). arXiv, 2023.
38. Boris N Oreshkin, Dmitri Carpov, Nicolas Chapados, and Yoshua Bengio. N-beats: Neural basis expansion analysis for interpretable time series forecasting. Journal of Machine Learning Research, 21(111):1–63, 2020. [find](https://scholar.google.com/scholar?q=Boris+N+Oreshkin%2C+Dmitri+Carpov%2C+Nicolas+Chapados%2C+and+Yoshua+Bengio%2E+N%2Dbeats%3A+Neural+basis+expansion+analysis+for+interpretable+time+series+forecasting%2E+Journal+of+Machine+Learning+Research%2C+21%28111%29%3A)
39. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. [Training language models to follow instructions with human feedback](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/). Advances in Neural Information Processing Systems, 35:27730–27744, 2022.
40. Liudmila Prokhorenkova, Gleb Gusev, Aleksandr Vorobev, Anna Veronika Dorogush, and Andrey Gulin. Catboost: unbiased boosting with categorical features. In Advances in Neural Information Processing Systems, volume 31, pages 6638–6648. NeurIPS, 2018. [find](https://scholar.google.com/scholar?q=Liudmila+Prokhorenkova%2C+Gleb+Gusev%2C+Aleksandr+Vorobev%2C+Anna+Veronika+Dorogush%2C+and+Andrey+Gulin%2E+Catboost%3A+unbiased+boosting+with+categorical+features%2E+In+Advances+in+Neural+Information+Processing+Sys)
41. David Salinas, Valentin Flunkert, Jan Gasthaus, and Tim Januschowski. Deepar: Probabilistic forecasting with autoregressive recurrent networks. International Journal of Forecasting, 36(3): 1181–1191, 2020. [find](https://scholar.google.com/scholar?q=David+Salinas%2C+Valentin+Flunkert%2C+Jan+Gasthaus%2C+and+Tim+Januschowski%2E+Deepar%3A+Probabilistic+forecasting+with+autoregressive+recurrent+networks%2E+International+Journal+of+Forecasting%2C+36%283%29%3A+1181%E2%80%931191%2C+)
42. Avi Schwarzschild, Eitan Borgnia, Arjun Gupta, Furong Huang, Uzi Vishkin, Micah Goldblum, and Tom Goldstein. Can you learn an algorithm? generalizing from easy to hard problems with recurrent networks. Advances in Neural Information Processing Systems, 34:6695–6706, 2021. [find](https://scholar.google.com/scholar?q=Avi+Schwarzschild%2C+Eitan+Borgnia%2C+Arjun+Gupta%2C+Furong+Huang%2C+Uzi+Vishkin%2C+Micah+Goldblum%2C+and+Tom+Goldstein%2E+Can+you+learn+an+algorithm%3F+generalizing+from+easy+to+hard+problems+with+recurrent+networks)
43. Ilya Sutskever. An observation on generalization. Workshop on Large Language Models and Transformers, 2023. URL [https://www.youtube.com/watch?v=AKMuA_TVz3A&ab_channel=SimonsInstitute](https://www.youtube.com/watch?v=AKMuA_TVz3A&ab_channel=SimonsInstitute). [↗](https://www.youtube.com/watch?v=AKMuA_TVz3A&ab_channel=SimonsInstitute)
44. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, et al. [Llama: Open and efficient foundation language models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-open-efficient-foundation-language/). arXiv preprint arXiv:2302.13971, 2023.
45. Hugo Touvron, Louis Martin, Kevin R. Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Daniel M. Bikel, Lukas Blecher, Cristian Canton Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, Bria… — [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-2-open-foundation-fine/)
46. Juan R Trapero, Nikolaos Kourentzes, and Robert Fildes. On the identification of sales forecasting models in the presence of promotions. Journal of the operational Research Society, 66(2): 299–307, 2015. [find](https://scholar.google.com/scholar?q=Juan+R+Trapero%2C+Nikolaos+Kourentzes%2C+and+Robert+Fildes%2E+On+the+identification+of+sales+forecasting+models+in+the+presence+of+promotions%2E+Journal+of+the+operational+Research+Society%2C+66%282%29%3A+299%E2%80%93307%2C+20)
47. Jason Wei, Maarten Bosma, Vincent Y Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M Dai, and Quoc V Le. [Finetuned language models are zero-shot learners](https://md.research.elamur.ai/free/en/papers/wei-2021-finetuned-language-models-zero-shot/). arXiv preprint arXiv:2109.01652, 2021.
48. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Ed Chi, Quoc Le, and Denny Zhou. Chain of thought prompting elicits reasoning in large language models. arXiv preprint arXiv:2201.[11903, 2022](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/).
49. Andrew Wilson and Ryan Adams. Gaussian process kernels for pattern discovery and extrapolation. In International conference on machine learning, pages 1067–1075. PMLR, 2013. [find](https://scholar.google.com/scholar?q=Andrew+Wilson+and+Ryan+Adams%2E+Gaussian+process+kernels+for+pattern+discovery+and+extrapolation%2E+In+International+conference+on+machine+learning%2C+pages+1067%E2%80%931075%2E+PMLR%2C+2013%2E)
50. Haixu Wu, Jiehui Xu, Jianmin Wang, and Mingsheng Long. Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. Advances in Neural Information Processing Systems, 34, 2021. [find](https://scholar.google.com/scholar?q=Haixu+Wu%2C+Jiehui+Xu%2C+Jianmin+Wang%2C+and+Mingsheng+Long%2E+Autoformer%3A+Decomposition+transformers+with+auto%2Dcorrelation+for+long%2Dterm+series+forecasting%2E+Advances+in+Neural+Information+Processing+Systems%2C)
51. Hao Xue and Flora D. Salim. Promptcast: A new prompt-based learning paradigm for time series forecasting, 2023. [find](https://scholar.google.com/scholar?q=Hao+Xue+and+Flora+D%2E+Salim%2E+Promptcast%3A+A+new+prompt%2Dbased+learning+paradigm+for+time+series+forecasting%2C+2023%2E)
52. Zheng Yuan, Hongyi Yuan, Chuanqi Tan, Wei Wang, and Songfang Huang. [How well do large language models perform in arithmetic tasks?](https://md.research.elamur.ai/free/en/papers/yuan-2023-well-large-language-models-perform/) arXiv preprint arXiv:2304.02015, 2023.
53. Ailing Zeng, Muxi Chen, Lei Zhang, and Qiang Xu. Are transformers effective for time series forecasting? arXiv preprint arXiv:2205.13504, 2022. [find](https://scholar.google.com/scholar?q=Ailing+Zeng%2C+Muxi+Chen%2C+Lei+Zhang%2C+and+Qiang+Xu%2E+Are+transformers+effective+for+time+series+forecasting%3F+arXiv+preprint+arXiv%3A2205%2E13504%2C+2022%2E)
54. Yiyuan Zhang, Kaixiong Gong, Kaipeng Zhang, Hongsheng Li, Yu Qiao, Wanli Ouyang, and Xiangyu Yue. Meta-transformer: A unified framework for multimodal learning. arXiv preprint arXiv:2307.10802, 2023. — [arXiv:2307.10802](https://arxiv.org/abs/2307.10802) [find](https://scholar.google.com/scholar?q=Yiyuan+Zhang%2C+Kaixiong+Gong%2C+Kaipeng+Zhang%2C+Hongsheng+Li%2C+Yu+Qiao%2C+Wanli+Ouyang%2C+and+Xiangyu+Yue%2E+Meta%2Dtransformer%3A+A+unified+framework+for+multimodal+learning%2E+arXiv+preprint+arXiv%3A2307%2E10802%2C+2023%2E+)
55. Haoyi Zhou, Shanghang Zhang, Jieqi Peng, Shuai Zhang, Jianxin Li, Hui Xiong, and Wancai Zhang. Informer: Beyond efficient transformer for long sequence time-series forecasting. In Proceedings of AAAI, 2021. [find](https://scholar.google.com/scholar?q=Haoyi+Zhou%2C+Shanghang+Zhang%2C+Jieqi+Peng%2C+Shuai+Zhang%2C+Jianxin+Li%2C+Hui+Xiong%2C+and+Wancai+Zhang%2E+Informer%3A+Beyond+efficient+transformer+for+long+sequence+time%2Dseries+forecasting%2E+In+Proceedings+of+AAAI%2C)
56. Tian Zhou, Ziqing Ma, Qingsong Wen, Xue Wang, Liang Sun, and Rong Jin. FEDformer: Frequency enhanced decomposed transformer for long-term series forecasting. In Proc. 39th International Conference on Machine Learning (ICML 2022), 2022. [find](https://scholar.google.com/scholar?q=Tian+Zhou%2C+Ziqing+Ma%2C+Qingsong+Wen%2C+Xue+Wang%2C+Liang+Sun%2C+and+Rong+Jin%2E+FEDformer%3A+Frequency+enhanced+decomposed+transformer+for+long%2Dterm+series+forecasting%2E+In+Proc%2E+39th+International+Conference+on+)
57. Tian Zhou, Peisong Niu, Xue Wang, Liang Sun, and Rong Jin. One fits all: Power general time series analysis by pretrained lm. arXiv preprint arXiv:2302.11939, 2023. [find](https://scholar.google.com/scholar?q=Tian+Zhou%2C+Peisong+Niu%2C+Xue+Wang%2C+Liang+Sun%2C+and+Rong+Jin%2E+One+fits+all%3A+Power+general+time+series+analysis+by+pretrained+lm%2E+arXiv+preprint+arXiv%3A2302%2E11939%2C+2023%2E)

*Updated 2 November 2026*