---
title: "MLCopilot — paper by Zhang et al. (2024) — summary and ideas"
description: "Configuring machine learning solutions for new tasks takes a lot of effort. 49 references, cited by 26 papers here."
authors: ["Lei Zhang", "Yuge Zhang", "Kan Ren", "Dongsheng Li", "Yuqing Yang"]
year: 2024
venue: "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2024.eacl-long.179/"
doi: "10.18653/v1/2024.eacl-long.179"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/zhang-2024-mlcopilot-unleashing-power-large-language/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhang-2024-mlcopilot-unleashing-power-large-language/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2024](https://md.research.elamur.ai/free/en/papers/2024/page/5/) / MLCopilot: Unleashing the Power of Large Language Models in Solving Machine Learning Tasks

# MLCopilot: Unleashing the Power of Large Language Models in Solving Machine Learning Tasks

**Authors:** [Lei Zhang](https://md.research.elamur.ai/free/en/authors/lei-zhang/), Yuge Zhang, Kan Ren, [Dongsheng Li](https://md.research.elamur.ai/free/en/authors/dongsheng-li/) and [Yuqing Yang](https://md.research.elamur.ai/free/en/authors/yuqing-yang/) · **Year:** 2024 · **Venue:** [Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/eacl/) ([EACL 2024](https://md.research.elamur.ai/free/en/venues/eacl/2024/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2024.eacl-long.179/) · [PDF](https://aclanthology.org/2024.eacl-long.179.pdf) · [DOI 10.18653/v1/2024.eacl-long.179](https://doi.org/10.18653/v1/2024.eacl-long.179) · [OpenAlex](https://openalex.org/W4411630043)

**Citations:** 26 citations (OpenAlex, 2026-10-14) · [26](https://md.research.elamur.ai/free/en/papers/zhang-2024-mlcopilot-unleashing-power-large-language/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Configuring machine learning solutions for new tasks takes a lot of effort. AutoML tools such as Bayesian optimization need many costly trials, ignore earlier tasks, and are hard for developers to interpret. MLCopilot is a framework that uses large language models (GPT-3.5) to propose ML solutions the way a human engineer might, by drawing on past experience.

It works in two stages:
- **Offline:** heterogeneous historical records (code, configs, logs) are canonicalized into an experience pool. The LLM then extracts high-level, human-readable knowledge from it, and a post-validation step filters that knowledge.
- **Online:** the system retrieves experiences and knowledge from the tasks most similar to the user's description. It then prompts the LLM to output several candidate solutions in a single round, with no search or optimization.

On benchmarks including HPO-B, PD1 and HyperFD, it performs comparably to or better than existing methods while answering almost instantly. The work suggests LLMs can handle structured inputs and reasoning beyond plain text. The authors see MLCopilot as a fast complement to AutoML rather than a replacement.

## Key points
- The authors claim to be the first to use LLMs to generate solutions for new ML tasks. Their retrieve-and-prompt pipeline returns multiple solutions without time-consuming search.
- Without historical experience, an LLM given only the task description performs about as well as random generation.
- In ablations, removing knowledge retrieval in the online stage clearly lowers performance. Offline post-validation reduces trivial, vague or hallucinated knowledge, though hallucinations still occasionally appear (e.g., on the UniRef50/Transformer task in PD1).
- To check for data leakage, the authors evaluated on HyperFD, a private dataset released after GPT-3.5's knowledge cutoff. Performance there remained robust, and canonicalizing the data improved results, which argues against simple memorization.
- Performance saturates at about three suggested solutions (t = 3). It can degrade when the prompt context window is very limited.
- Code and examples are available at github.com/microsoft/CoML.

*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

- [Microsoft](https://md.research.elamur.ai/free/en/companies/microsoft/) — Company, Redmond, United States · 325 works · 142,931 citations
- [ShanghaiTech University](https://md.research.elamur.ai/free/en/universities/shanghaitech-university/) — University, Shanghai, China · 13 works · 1,974 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

🧭 Topics (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works

## Cite

Cite as: Lei Zhang, Yuge Zhang, Kan Ren, Dongsheng Li and Yuqing Yang. 2024. MLCopilot: Unleashing the Power of Large Language Models in Solving Machine Learning Tasks. Proceedings of the 18th Conference of the European Chapter 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.

```bibtex
@inproceedings{zhang2024mlcopilot,
  title = {{MLCopilot: Unleashing the Power of Large Language Models in Solving Machine Learning Tasks}},
  author = {Lei Zhang, Yuge Zhang, Kan Ren, Dongsheng Li and Yuqing Yang},
  booktitle = {Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2024},
  doi = {10.18653/v1/2024.eacl-long.179},
  url = {https://doi.org/10.18653/v1/2024.eacl-long.179}
}
```

- [← previous LLM Internal States Reveal Hallucination Risk Faced With a Query](https://md.research.elamur.ai/free/en/papers/ji-2024-llm-internal-states-reveal-hallucination/)
- [next → Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Proving](https://md.research.elamur.ai/free/en/papers/quan-2024-verification-refinement-natural-language-explanations/)
- [↑ back to papers of 2024](https://md.research.elamur.ai/free/en/papers/2024/page/5/)

## References

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

1. Marcin Andrychowicz, Misha Denil, Sergio Gomez, Matthew W Hoffman, David Pfau, Tom Schaul, Brendan Shillingford, and Nando De Freitas. 2016. Learning to learn by gradient descent by gradient descent. Advances in neural information processing systems, 29. [find](https://scholar.google.com/scholar?q=Marcin+Andrychowicz%2C+Misha+Denil%2C+Sergio+Gomez%2C+Matthew+W+Hoffman%2C+David+Pfau%2C+Tom+Schaul%2C+Brendan+Shillingford%2C+and+Nando+De+Freitas%2E+2016%2E+Learning+to+learn+by+gradient+descent+by+gradient+descent%2E+)
2. Sebastian Pineda Arango, Hadi Samer Jomaa, Martin Wistuba, and Josif Grabocka. 2021. Hpo-b: A large-scale reproducible benchmark for black-box hpo based on openml. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2). [find](https://scholar.google.com/scholar?q=Sebastian+Pineda+Arango%2C+Hadi+Samer+Jomaa%2C+Martin+Wistuba%2C+and+Josif+Grabocka%2E+2021%2E+Hpo%2Db%3A+A+large%2Dscale+reproducible+benchmark+for+black%2Dbox+hpo+based+on+openml%2E+In+Thirty%2Dfifth+Conference+on+Neural)
3. Rémi Bardenet, Mátyás Brendel, Balázs Kégl, and Michele Sebag. 2013. Collaborative hyperparameter tuning. In International conference on machine learning, pages 199–207. PMLR. [find](https://scholar.google.com/scholar?q=R%C3%A9mi+Bardenet%2C+M%C3%A1ty%C3%A1s+Brendel%2C+Bal%C3%A1zs+K%C3%A9gl%2C+and+Michele+Sebag%2E+2013%2E+Collaborative+hyperparameter+tuning%2E+In+International+conference+on+machine+learning%2C+pages+199%E2%80%93207%2E+PMLR%2E)
4. Christopher M Bishop and Nasser M Nasrabadi. 2006. Pattern recognition and machine learning, volume 4. Springer. [find](https://scholar.google.com/scholar?q=Christopher+M+Bishop+and+Nasser+M+Nasrabadi%2E+2006%2E+Pattern+recognition+and+machine+learning%2C+volume+4%2E+Springer%2E)
5. Jie Huang and Kevin Chen-Chuan Chang. 2022. [Towards reasoning in large language models: A survey](https://md.research.elamur.ai/free/en/papers/huang-2023-reasoning-large-language-models-survey/). arXiv preprint arXiv:2212.10403.
6. Daniil A. Boiko, Robert MacKnight, and Gabe Gomes. 2023. Emergent autonomous scientific research capabilities of large language models. [find](https://scholar.google.com/scholar?q=Daniil+A%2E+Boiko%2C+Robert+MacKnight%2C+and+Gabe+Gomes%2E+2023%2E+Emergent+autonomous+scientific+research+capabilities+of+large+language+models%2E)
7. Frank Hutter, Lars Kotthoff, and Joaquin Vanschoren. 2019. Automated machine learning: methods, systems, challenges. Springer Nature. [find](https://scholar.google.com/scholar?q=Frank+Hutter%2C+Lars+Kotthoff%2C+and+Joaquin+Vanschoren%2E+2019%2E+Automated+machine+learning%3A+methods%2C+systems%2C+challenges%2E+Springer+Nature%2E)
8. Leo Breiman. 2001. Random forests. Machine learning, 45:5–32. [find](https://scholar.google.com/scholar?q=Leo+Breiman%2E+2001%2E+Random+forests%2E+Machine+learning%2C+45%3A5%E2%80%9332%2E)
9. Shima Imani, Liang Du, and Harsh Shrivastava. 2023. [Mathprompter: Mathematical reasoning using large language models](https://md.research.elamur.ai/free/en/papers/imani-2023-mathprompter-mathematical-reasoning-large-language/).
10. Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter,… — [Language Models are Few-Shot Learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/)
11. Tianqi Chen and Carlos Guestrin. 2016. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pages 785– 794. [find](https://scholar.google.com/scholar?q=Tianqi+Chen+and+Carlos+Guestrin%2E+2016%2E+Xgboost%3A+A+scalable+tree+boosting+system%2E+In+Proceedings+of+the+22nd+acm+sigkdd+international+conference+on+knowledge+discovery+and+data+mining%2C+pages+785%E2%80%93+794%2E)
12. Yutian Chen, Xingyou Song, Chansoo Lee, Zi Wang, Richard Zhang, David Dohan, Kazuya Kawakami, Greg Kochanski, Arnaud Doucet, Marc’aurelio Ranzato, et al. 2022. Towards learning universal hyperparameter optimizers with transformers. Advances in Neural Information Processing Systems, 35:32053– 32068. [find](https://scholar.google.com/scholar?q=Yutian+Chen%2C+Xingyou+Song%2C+Chansoo+Lee%2C+Zi+Wang%2C+Richard+Zhang%2C+David+Dohan%2C+Kazuya+Kawakami%2C+Greg+Kochanski%2C+Arnaud+Doucet%2C+Marc%E2%80%99aurelio+Ranzato%2C+et+al%2E+2022%2E+Towards+learning+universal+hyperparamete)
13. Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, and others. 2022. [Palm: Scaling language modeling with pathways](https://md.research.elamur.ai/free/en/papers/chowdhery-2022-palm-scaling-language-modeling-pathways/). ArXiv, abs/2204.02311.
14. Corinna Cortes and Vladimir Vapnik. 1995. [Support-vector networks](https://md.research.elamur.ai/free/en/papers/cortes-1995-support-vector-networks/). Machine learning, 20:273–297.
15. Oxford English Dictionary. 1989. Oxford english dictionary. Simpson, Ja & Weiner, Esc, 3. [find](https://scholar.google.com/scholar?q=Oxford+English+Dictionary%2E+1989%2E+Oxford+english+dictionary%2E+Simpson%2C+Ja+%26+Weiner%2C+Esc%2C+3%2E)
16. Matthias Feurer, Aaron Klein, Katharina Eggensperger, Jost Springenberg, Manuel Blum, and Frank Hutter. 2015. Efficient and robust automated machine learning. Advances in neural information processing systems, 28. [find](https://scholar.google.com/scholar?q=Matthias+Feurer%2C+Aaron+Klein%2C+Katharina+Eggensperger%2C+Jost+Springenberg%2C+Manuel+Blum%2C+and+Frank+Hutter%2E+2015%2E+Efficient+and+robust+automated+machine+learning%2E+Advances+in+neural+information+processing)
17. Peter I Frazier. 2018. A tutorial on bayesian optimization. arXiv preprint arXiv:1807.02811. — [arXiv:1807.02811](https://arxiv.org/abs/1807.02811) [find](https://scholar.google.com/scholar?q=Peter+I+Frazier%2E+2018%2E+A+tutorial+on+bayesian+optimization%2E+arXiv+preprint+arXiv%3A1807%2E02811%2E+%E2%80%94+%5BarXiv%3A1807%2E02811%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1807%2E02811%29)
18. Hongwei Han, Jialiang Xu, Mengyu Zhou, Yijia Shao, Shi Han, and Dongmei Zhang. 2022. Luna: Language understanding with number augmentations on transformers via number plugins and pre-training. arXiv preprint arXiv:2212.02691. — [arXiv:2212.02691](https://arxiv.org/abs/2212.02691) [find](https://scholar.google.com/scholar?q=Hongwei+Han%2C+Jialiang+Xu%2C+Mengyu+Zhou%2C+Yijia+Shao%2C+Shi+Han%2C+and+Dongmei+Zhang%2E+2022%2E+Luna%3A+Language+understanding+with+number+augmentations+on+transformers+via+number+plugins+and+pre%2Dtraining%2E+arXiv+p)
19. Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Ye Jin Bang, Andrea Madotto, and Pascale Fung. 2023. [Survey of hallucination in natural language generation](https://md.research.elamur.ai/free/en/papers/ji-2022-survey-hallucination-natural-language-generation/). ACM Computing Surveys, 55(12):1–38.
20. Lars Kotthoff, Chris Thornton, Holger H Hoos, Frank Hutter, and Kevin Leyton-Brown. 2019. Auto-weka: Automatic model selection and hyperparameter optimization in weka. Automated machine learning: methods, systems, challenges, pages 81–95. [find](https://scholar.google.com/scholar?q=Lars+Kotthoff%2C+Chris+Thornton%2C+Holger+H+Hoos%2C+Frank+Hutter%2C+and+Kevin+Leyton%2DBrown%2E+2019%2E+Auto%2Dweka%3A+Automatic+model+selection+and+hyperparameter+optimization+in+weka%2E+Automated+machine+learning%3A+meth)
21. Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2017. Imagenet classification with deep convolutional neural networks. Communications of the ACM, 60(6):84–90. [find](https://scholar.google.com/scholar?q=Alex+Krizhevsky%2C+Ilya+Sutskever%2C+and+Geoffrey+E+Hinton%2E+2017%2E+Imagenet+classification+with+deep+convolutional+neural+networks%2E+Communications+of+the+ACM%2C+60%286%29%3A84%E2%80%9390%2E)
22. Pan Lu, Baolin Peng, Hao Cheng, Michel Galley, Kai-Wei Chang, Ying Nian Wu, Song-Chun Zhu, and Jianfeng Gao. 2023. [Chameleon: Plug-and-play compositional reasoning with large language models](https://md.research.elamur.ai/free/en/papers/lu-2023-chameleon-plug-play-compositional-reasoning/). arXiv preprint arXiv:2304.09842.
23. Yao Lu, Max Bartolo, Alastair Moore, Sebastian Riedel, and Pontus Stenetorp. 2022. [Fantastically ordered prompts and where to find them: Overcoming few-shot prompt order sensitivity](https://md.research.elamur.ai/free/en/papers/lu-2022-fantastically-ordered-prompts-where-find/). In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), p…
24. Sewon Min, Xinxi Lyu, Ari Holtzman, Mikel Artetxe, Mike Lewis, Hannaneh Hajishirzi, and Luke Zettlemoyer. 2022. [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://md.research.elamur.ai/free/en/papers/min-2022-rethinking-role-demonstrations-what-makes/) In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association f…
25. Gaurav Mittal, Chang Liu, Nikolaos Karianakis, Victor Fragoso, Mei Chen, and Yun Fu. 2020. Hyperstar: Task-aware hyperparameters for deep networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8736– 8745. [find](https://scholar.google.com/scholar?q=Gaurav+Mittal%2C+Chang+Liu%2C+Nikolaos+Karianakis%2C+Victor+Fragoso%2C+Mei+Chen%2C+and+Yun+Fu%2E+2020%2E+Hyperstar%3A+Task%2Daware+hyperparameters+for+deep+networks%2E+In+Proceedings+of+the+IEEE%2FCVF+Conference+on+Compute)
26. Yurii Evgen’evich Nesterov. 1983. A method of solving a convex programming problem with convergence rate o\\bigl(kˆ2\\bigr). In Doklady Akademii Nauk, volume 269, pages 543–547. Russian Academy of Sciences. [find](https://scholar.google.com/scholar?q=Yurii+Evgen%E2%80%99evich+Nesterov%2E+1983%2E+A+method+of+solving+a+convex+programming+problem+with+convergence+rate+o%5C%5Cbigl%28k%CB%862%5C%5Cbigr%29%2E+In+Doklady+Akademii+Nauk%2C+volume+269%2C+pages+543%E2%80%93547%2E+Russian+Academy+of+Sci)
27. OpenAI. 2023. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/).
28. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. [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.
29. Arkil Patel, Satwik Bhattamishra, and Navin Goyal. 2021. [Are nlp models really able to solve simple math word problems?](https://md.research.elamur.ai/free/en/papers/patel-2021-are-nlp-models-really-able/) arXiv preprint arXiv:2103.07191.
30. Hieu Pham, Melody Guan, Barret Zoph, Quoc Le, and Jeff Dean. 2018. Efficient neural architecture search via parameters sharing. In International conference on machine learning, pages 4095–4104. PMLR. [find](https://scholar.google.com/scholar?q=Hieu+Pham%2C+Melody+Guan%2C+Barret+Zoph%2C+Quoc+Le%2C+and+Jeff+Dean%2E+2018%2E+Efficient+neural+architecture+search+via+parameters+sharing%2E+In+International+conference+on+machine+learning%2C+pages+4095%E2%80%934104%2E+PMLR%2E)
31. Alec Radford, Karthik Narasimhan, Tim Salimans, and Ilya Sutskever. 2018. Improving language understanding by generative pre-training. [find](https://scholar.google.com/scholar?q=Alec+Radford%2C+Karthik+Narasimhan%2C+Tim+Salimans%2C+and+Ilya+Sutskever%2E+2018%2E+Improving+language+understanding+by+generative+pre%2Dtraining%2E)
32. Alec Radford, Jeff Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. [find](https://scholar.google.com/scholar?q=Alec+Radford%2C+Jeff+Wu%2C+Rewon+Child%2C+David+Luan%2C+Dario+Amodei%2C+and+Ilya+Sutskever%2E+2019%2E+Language+models+are+unsupervised+multitask+learners%2E)
33. David Saxton, Edward Grefenstette, Felix Hill, and Pushmeet Kohli. 2019. [Analysing mathematical reasoning abilities of neural models](https://md.research.elamur.ai/free/en/papers/saxton-2019-analysing-mathematical-reasoning-abilities-neural/). arXiv preprint arXiv:1904.01557.
34. Yongliang Shen, Kaitao Song, Xu Tan, Dongsheng Li, Weiming Lu, and Yueting Zhuang. 2023. [Hugginggpt: Solving ai tasks with chatgpt and its friends in huggingface](https://md.research.elamur.ai/free/en/papers/shen-2023-hugginggpt-solving-ai-tasks-chatgpt/). arXiv preprint arXiv:2303.17580.
35. Richard S Sutton and Andrew G Barto. 2018. Reinforcement learning: An introduction. MIT press. [find](https://scholar.google.com/scholar?q=Richard+S+Sutton+and+Andrew+G+Barto%2E+2018%2E+Reinforcement+learning%3A+An+introduction%2E+MIT+press%2E)
36. Avijit Thawani, Jay Pujara, Pedro A Szekely, and Filip Ilievski. 2021. Representing numbers in nlp: a survey and a vision. arXiv preprint arXiv:2103.13136. [find](https://scholar.google.com/scholar?q=Avijit+Thawani%2C+Jay+Pujara%2C+Pedro+A+Szekely%2C+and+Filip+Ilievski%2E+2021%2E+Representing+numbers+in+nlp%3A+a+survey+and+a+vision%2E+arXiv+preprint+arXiv%3A2103%2E13136%2E)
37. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aur’elien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. [Llama: Open and Efficient Foundation Language Models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-open-efficient-foundation-language/). ArXiv,…
38. Joaquin Vanschoren, Jan N Van Rijn, Bernd Bischl, and Luis Torgo. 2014. Openml: networked science in machine learning. ACM SIGKDD Explorations Newsletter, 15(2):49–60. [find](https://scholar.google.com/scholar?q=Joaquin+Vanschoren%2C+Jan+N+Van+Rijn%2C+Bernd+Bischl%2C+and+Luis+Torgo%2E+2014%2E+Openml%3A+networked+science+in+machine+learning%2E+ACM+SIGKDD+Explorations+Newsletter%2C+15%282%29%3A49%E2%80%9360%2E)
39. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. [Attention is all you need](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/). Advances in neural information processing systems, 30.
40. Zi Wang, George E Dahl, Kevin Swersky, Chansoo Lee, Zelda Mariet, Zachary Nado, Justin Gilmer, Jasper Snoek, and Zoubin Ghahramani. 2021b. Pre-trained gaussian processes for bayesian optimization. arXiv preprint arXiv:2109.08215. — [arXiv:2109.08215](https://arxiv.org/abs/2109.08215) [find](https://scholar.google.com/scholar?q=Zi+Wang%2C+George+E+Dahl%2C+Kevin+Swersky%2C+Chansoo+Lee%2C+Zelda+Mariet%2C+Zachary+Nado%2C+Justin+Gilmer%2C+Jasper+Snoek%2C+and+Zoubin+Ghahramani%2E+2021b%2E+Pre%2Dtrained+gaussian+processes+for+bayesian+optimization%2E+arX)
41. Albert Webson and Ellie Pavlick. 2022. [Do prompt-based models really understand the meaning of their prompts?](https://md.research.elamur.ai/free/en/papers/webson-2022-do-prompt-based-models-really/) In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2300–2344.
42. Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, E. Chi, Tatsunori Hashimoto, Oriol Vinyals, P. Liang, J. Dean, and W. Fedus. 2022. [Emergent Abilities of Large Language Models](https://md.research.elamur.ai/free/en/papers/wei-2022-emergent-abilities-large-language-models/). ArXiv, abs/2206.07682.
43. Martin Wistuba, Nicolas Schilling, and Lars Schmidt-Thieme. 2016. Two-stage transfer surrogate model for automatic hyperparameter optimization. In Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2016, Riva del Garda, Italy, September 19-23, 2016, Proceedings, Pa… [find](https://scholar.google.com/scholar?q=Martin+Wistuba%2C+Nicolas+Schilling%2C+and+Lars+Schmidt%2DThieme%2E+2016%2E+Two%2Dstage+transfer+surrogate+model+for+automatic+hyperparameter+optimization%2E+In+Machine+Learning+and+Knowledge+Discovery+in+Databases)
44. Chenqian Yan, Yuge Zhang, Quanlu Zhang, Yaming Yang, Xinyang Jiang, Yuqing Yang, and Baoyuan Wang. 2022. Privacy-preserving online automl for domain-specific face detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4134–4144. [find](https://scholar.google.com/scholar?q=Chenqian+Yan%2C+Yuge+Zhang%2C+Quanlu+Zhang%2C+Yaming+Yang%2C+Xinyang+Jiang%2C+Yuqing+Yang%2C+and+Baoyuan+Wang%2E+2022%2E+Privacy%2Dpreserving+online+automl+for+domain%2Dspecific+face+detection%2E+In+Proceedings+of+the+IEEE)
45. Wenhao Yu, Dan Iter, Shuohang Wang, Yichong Xu, Mingxuan Ju, Soumya Sanyal, Chenguang Zhu, Michael Zeng, and Meng Jiang. 2022. [Generate rather than retrieve: Large language models are strong context generators](https://md.research.elamur.ai/free/en/papers/yu-2022-generate-rather-than-retrieve-large/). arXiv preprint arXiv:2209.10063.
46. Ningyu Zhang, Xin Xu, Liankuan Tao, Haiyang Yu, Hongbin Ye, Shuofei Qiao, Xin Xie, Xiang Chen, Zhoubo Li, Lei Li, et al. 2022. Deepke: A deep learning based knowledge extraction toolkit for knowledge base population. arXiv preprint arXiv:2201.03335. [find](https://scholar.google.com/scholar?q=Ningyu+Zhang%2C+Xin+Xu%2C+Liankuan+Tao%2C+Haiyang+Yu%2C+Hongbin+Ye%2C+Shuofei+Qiao%2C+Xin+Xie%2C+Xiang+Chen%2C+Zhoubo+Li%2C+Lei+Li%2C+et+al%2E+2022%2E+Deepke%3A+A+deep+learning+based+knowledge+extraction+toolkit+for+knowledge+)
47. Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, et al. 2023. [A survey of large language models](https://md.research.elamur.ai/free/en/papers/zhao-2023-survey-large-language-models/). arXiv preprint arXiv:2303.18223.
48. Mingkai Zheng, Xiu Su, Shan You, Fei Wang, Chen Qian, Chang Xu, and Samuel Albanie. 2023. Can gpt-4 perform neural architecture search? [find](https://scholar.google.com/scholar?q=Mingkai+Zheng%2C+Xiu+Su%2C+Shan+You%2C+Fei+Wang%2C+Chen+Qian%2C+Chang+Xu%2C+and+Samuel+Albanie%2E+2023%2E+Can+gpt%2D4+perform+neural+architecture+search%3F)
49. Chi Wang, Qingyun Wu, Markus Weimer, and Erkang Zhu. 2021a. Flaml: A fast and lightweight automl library. Proceedings of Machine Learning and Systems, 3:434–447. [find](https://scholar.google.com/scholar?q=Chi+Wang%2C+Qingyun+Wu%2C+Markus+Weimer%2C+and+Erkang+Zhu%2E+2021a%2E+Flaml%3A+A+fast+and+lightweight+automl+library%2E+Proceedings+of+Machine+Learning+and+Systems%2C+3%3A434%E2%80%93447%2E)

*Updated 30 October 2026*