---
title: "Many-Shot In-Context Learning — Agarwal 2024"
description: "Few-shot in-context learning (ICL) used to be capped by short context windows, so it only ever saw a handful of examples."
authors: ["Rishabh Agarwal", "Avi Singh", "Lei M. Zhang", "Bernd Bohnet", "Luis Rosias", "Stephanie Chan", "Biao Zhang", "Ankesh Anand", "Zaheer Abbas", "Azade Nova", "John D. Co-Reyes", "Eric Chu", "Feryal Behbahani", "Aleksandra Faust", "Hugo Larochelle"]
year: 2024
venue: "arXiv:2404.11018"
source: "https://arxiv.org/abs/2404.11018"
doi: "10.48550/arxiv.2404.11018"
arxiv: "2404.11018"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/agarwal-2024-many-shot-context-learning/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/agarwal-2024-many-shot-context-learning/)

[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/3/) / Many-Shot In-Context Learning

# Many-Shot In-Context Learning

**Authors:** [Rishabh Agarwal](https://md.research.elamur.ai/free/en/authors/rishabh-agarwal/), [Avi Singh](https://md.research.elamur.ai/free/en/authors/avi-singh/), [Lei M. Zhang](https://md.research.elamur.ai/free/en/authors/lei-m-zhang/), [Bernd Bohnet](https://md.research.elamur.ai/free/en/authors/bernd-bohnet/), Luis Rosias, [Stephanie Chan](https://md.research.elamur.ai/free/en/authors/stephanie-chan/), [Biao Zhang](https://md.research.elamur.ai/free/en/authors/biao-zhang/), [Ankesh Anand](https://md.research.elamur.ai/free/en/authors/ankesh-anand/), Zaheer Abbas, Azade Nova, [John D. Co-Reyes](https://md.research.elamur.ai/free/en/authors/john-d-co-reyes/), [Eric Chu](https://md.research.elamur.ai/free/en/authors/eric-chu/) et al. (15 authors) · **Year:** 2024 · **Venue:** arXiv:2404.11018 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2404.11018) · [PDF](https://arxiv.org/pdf/2404.11018) · [DOI 10.48550/arxiv.2404.11018](https://doi.org/10.48550/arxiv.2404.11018) · [arXiv 2404.11018](https://arxiv.org/abs/2404.11018) · [OpenAlex](https://openalex.org/W4415796795)

**Citations:** 22 citations (openalex-snapshot · 2026-10-14) · [111](#cited-by) in our library, of the 140673 papers whose bibliographies we read

## Summary
Few-shot in-context learning (ICL) used to be capped by short context windows, so it only ever saw a handful of examples. Context windows now reach about a million tokens, and this paper asks what happens when a prompt holds hundreds or thousands of demonstrations. Using Gemini 1.5 Pro, the authors scale the number of shots on a broad set of tasks: math (MATH, GSM8K), GPQA, BIG-Bench Hard, summarization (XSum, XLSum), low-resource translation (FLORES-200), Logistics planning, code verification and sentiment analysis. Moving from few to many shots brings large gains on most tasks, and the best results often need prompts of hundreds of thousands of tokens. Good human-written outputs can be scarce, so the authors propose two alternatives. Reinforced ICL uses model-generated rationales that are filtered for correct answers. Unsupervised ICL supplies only problems, with no solutions. Both help on reasoning tasks. The analysis shows that many-shot prompts can override pretraining biases, learn numeric functions in many dimensions and roughly match full fine-tuning. This suggests long-context prompting could partly replace task-specific training, which matters especially for low-resource languages.

## Key points
- **Translation:** the authors used all 997 FLORES dev pairs, a prompt of about 85K tokens. Compared with a 1-shot prompt, chrF2++ rose by 15.3% for English→Bemba and 4.5% for English→Kurdish. Both results beat the previous best scores, set by NLLB (Bemba) and Google Translate (Kurdish).
- **Scale:** the experiments went up to 8192 shots and up to 1M tokens of context. On some tasks, performance gets worse past a certain number of shots; examples include XSum after about 50 shots, MATH, planning and code verification.
- **Summarization:** at its best, many-shot ICL comes close to fine-tuned PEGASUS and mT5. However, the model sometimes made up dates and times in its summaries.
- **Analysis tasks:** many-shot ICL handles sequential parity and linear classification, which few-shot ICL struggles with. The order of the examples still affects the results.
- **Next-token loss:** next-token prediction loss did not reliably predict ICL accuracy on reasoning tasks. Early tests with GPT-4-Turbo, Gemini 1.5 Flash and Claude-3-Opus suggest that other models also benefit from many-shot prompts.

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

Fields: [AI & machine learning](https://md.research.elamur.ai/free/en/shelves/ai/)

## Cited by

Cited by

111 papers of our library cite it (of the 140673 whose bibliographies we read); 7 of them have a page here, 104 not yet.

- [LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks](https://md.research.elamur.ai/free/en/papers/bai-2024-longbench-v2-deeper-understanding/)
- [A Survey on In-context Learning](https://md.research.elamur.ai/free/en/papers/dong-2023-survey-context-learning/)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://md.research.elamur.ai/free/en/papers/gemini-2024-team-gemini-1-5-unlocking-multimodal/)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://md.research.elamur.ai/free/en/papers/hsieh-2024-ruler-s-real-context-size/)
- [Tulu 3: Pushing Frontiers in Open Language Model Post-Training](https://md.research.elamur.ai/free/en/papers/lambert-2024-tulu-3-pushing-frontiers-open/)
- [Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models](https://md.research.elamur.ai/free/en/papers/singh-2023-human-data-scaling-self-training/)
- [Generative Verifiers: Reward Modeling as Next-Token Prediction](https://md.research.elamur.ai/free/en/papers/zhang-2024-generative-verifiers-reward-modeling-as/)

## Cite

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

```bibtex
@misc{agarwal2024many,
  title = {{Many-Shot In-Context Learning}},
  author = {Agarwal, Rishabh and Singh, Avi and Zhang, Lei M. and Bohnet, Bernd and Rosias, Luis and Chan, Stephanie and Zhang, Biao and Anand, Ankesh and Abbas, Zaheer and Nova, Azade and Co-Reyes, John D. and Chu, Eric and Behbahani, Feryal and Faust, Aleksandra and Larochelle, Hugo},
  year = {2024},
  doi = {10.48550/arxiv.2404.11018},
  eprint = {2404.11018},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2404.11018}
}
```

- [← previous MAmmoTH2: Scaling Instructions from the Web](https://md.research.elamur.ai/free/en/papers/yue-2024-mammoth2-scaling-instructions-web/)
- [next → Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://md.research.elamur.ai/free/en/papers/wang-2024-math-shepherd-verify-reinforce-llms/)
- [↑ back to papers of 2024](https://md.research.elamur.ai/free/en/papers/2024/page/3/)

## References

74 references, 26 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. S. N. Akter, Z. Yu, A. Muhamed, T. Ou, A. Bäuerle, Á. A. Cabrera, K. Dholakia, C. Xiong, and G. Neubig. An in-depth look at gemini’s language abilities. arXiv preprint arXiv:2312.11444, 2023. — [arXiv:2312.11444](https://arxiv.org/abs/2312.11444) [find](https://scholar.google.com/scholar?q=S%2E+N%2E+Akter%2C+Z%2E+Yu%2C+A%2E+Muhamed%2C+T%2E+Ou%2C+A%2E+B%C3%A4uerle%2C+%C3%81%2E+A%2E+Cabrera%2C+K%2E+Dholakia%2C+C%2E+Xiong%2C+and+G%2E+Neubig%2E+An+in%2Ddepth+look+at+gemini%E2%80%99s+language+abilities%2E+arXiv+preprint+arXiv%3A2312%2E11444%2C+2023%2E+%E2%80%94+%5BarXiv)
2. C. Anil, E. Durmus, M. Sharma, J. Benton, S. Kundu, J. Batson, N. Rimsky, M. Tong, J. Mu, D. Ford, F. Mosconi, R. Agrawal, R. Schaeffer, N. Bashkansky, S. Svenningsen, M. Lambert, A. Radhakrishnan, C. Denison, E. J. Hubinger, Y. Bai, T. Bricken, T. Maxwell, N. Schiefer, J. Sully, A. Tamkin, T. Lanha… [find](https://scholar.google.com/scholar?q=C%2E+Anil%2C+E%2E+Durmus%2C+M%2E+Sharma%2C+J%2E+Benton%2C+S%2E+Kundu%2C+J%2E+Batson%2C+N%2E+Rimsky%2C+M%2E+Tong%2C+J%2E+Mu%2C+D%2E+Ford%2C+F%2E+Mosconi%2C+R%2E+Agrawal%2C+R%2E+Schaeffer%2C+N%2E+Bashkansky%2C+S%2E+Svenningsen%2C+M%2E+Lambert%2C+A%2E+Radhakrishnan%2C+C%2E)
3. Anthropic. The claude 3 model family: Opus, sonnet, haiku. Technical Report, 2024. [find](https://scholar.google.com/scholar?q=Anthropic%2E+The+claude+3+model+family%3A+Opus%2C+sonnet%2C+haiku%2E+Technical+Report%2C+2024%2E)
4. A. Asai, S. Kudugunta, X. V. Yu, T. Blevins, H. Gonen, M. Reid, Y. Tsvetkov, S. Ruder, and H. Hajishirzi. Buffet: Benchmarking large language models for few-shot cross-lingual transfer. arXiv preprint arXiv:2305.14857, 2023. [find](https://scholar.google.com/scholar?q=A%2E+Asai%2C+S%2E+Kudugunta%2C+X%2E+V%2E+Yu%2C+T%2E+Blevins%2C+H%2E+Gonen%2C+M%2E+Reid%2C+Y%2E+Tsvetkov%2C+S%2E+Ruder%2C+and+H%2E+Hajishirzi%2E+Buffet%3A+Benchmarking+large+language+models+for+few%2Dshot+cross%2Dlingual+transfer%2E+arXiv+preprint)
5. A. Awadalla, M. Wortsman, G. Ilharco, S. Min, I. Magnusson, H. Hajishirzi, and L. Schmidt. Exploring the landscape of distributional robustness for question answering models. arXiv preprint arXiv:2210.12517, 2022. [find](https://scholar.google.com/scholar?q=A%2E+Awadalla%2C+M%2E+Wortsman%2C+G%2E+Ilharco%2C+S%2E+Min%2C+I%2E+Magnusson%2C+H%2E+Hajishirzi%2C+and+L%2E+Schmidt%2E+Exploring+the+landscape+of+distributional+robustness+for+question+answering+models%2E+arXiv+preprint+arXiv%3A2210)
6. A. Bertsch, M. Ivgi, U. Alon, J. Berant, M. R. Gormley, and G. Neubig. In-Context Learning with Long-Context Models: An In-Depth Exploration, Apr. 2024. URL http://arxiv.org/abs/ 2405.00200 . arXiv:2405.00200 [cs]. [↗](http://arxiv.org/abs/)
7. S. Bhattamishra, A. Patel, P. Blunsom, and V. Kanade. Understanding in-context learning in transformers and llms by learning to learn discrete functions. arXiv preprint arXiv:2310.03016, 2023. — [arXiv:2310.03016](https://arxiv.org/abs/2310.03016) [find](https://scholar.google.com/scholar?q=S%2E+Bhattamishra%2C+A%2E+Patel%2C+P%2E+Blunsom%2C+and+V%2E+Kanade%2E+Understanding+in%2Dcontext+learning+in+transformers+and+llms+by+learning+to+learn+discrete+functions%2E+arXiv+preprint+arXiv%3A2310%2E03016%2C+2023%2E+%E2%80%94+%5BarXi)
8. T. B. Brown, B. Mann, N. Ryder, M. Subbiah, J. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell, S. Agarwal, A. Herbert-Voss, G. Krueger, T. Henighan, R. Child, A. Ramesh, D. M. Ziegler, J. Wu, C. Winter, C. Hesse, M. Chen, E. Sigler, M. Litwin, S. Gray, B. Chess, J. Clark, C. Ber… [find](https://scholar.google.com/scholar?q=T%2E+B%2E+Brown%2C+B%2E+Mann%2C+N%2E+Ryder%2C+M%2E+Subbiah%2C+J%2E+Kaplan%2C+P%2E+Dhariwal%2C+A%2E+Neelakantan%2C+P%2E+Shyam%2C+G%2E+Sastry%2C+A%2E+Askell%2C+S%2E+Agarwal%2C+A%2E+Herbert%2DVoss%2C+G%2E+Krueger%2C+T%2E+Henighan%2C+R%2E+Child%2C+A%2E+Ramesh%2C+D%2E+M%2E+Zie)
9. S. C. Y. Chan, I. Dasgupta, J. Kim, D. Kumaran, A. K. Lampinen, and F. Hill. Transformers generalize differently from information stored in context vs in weights, Oct. 2022. URL http://arxiv.org/abs/2210.05675 . arXiv:2210.05675 [cs]. — [arXiv:2210.05675](https://arxiv.org/abs/2210.05675) [↗](http://arxiv.org/abs/2210.05675)
10. K. Cobbe, V. Kosaraju, M. Bavarian, M. Chen, H. Jun, L. Kaiser, M. Plappert, J. Tworek, J. Hilton, R. Nakano, C. Hesse, and J. Schulman. Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168, 2021. [find](https://scholar.google.com/scholar?q=K%2E+Cobbe%2C+V%2E+Kosaraju%2C+M%2E+Bavarian%2C+M%2E+Chen%2C+H%2E+Jun%2C+L%2E+Kaiser%2C+M%2E+Plappert%2C+J%2E+Tworek%2C+J%2E+Hilton%2C+R%2E+Nakano%2C+C%2E+Hesse%2C+and+J%2E+Schulman%2E+Training+verifiers+to+solve+math+word+problems%2E+arXiv+preprint+) [our card](https://md.research.elamur.ai/free/en/papers/cobbe-2021-training-verifiers-solve-math-word/)
11. T. Dinh, Y. Zeng, R. Zhang, Z. Lin, M. Gira, S. Rajput, J.-y. Sohn, D. Papailiopoulos, and K. Lee. Lift: Language-interfaced fine-tuning for non-language machine learning tasks. Advances in Neural Information Processing Systems, 35:11763–11784, 2022. [find](https://scholar.google.com/scholar?q=T%2E+Dinh%2C+Y%2E+Zeng%2C+R%2E+Zhang%2C+Z%2E+Lin%2C+M%2E+Gira%2C+S%2E+Rajput%2C+J%2E%2Dy%2E+Sohn%2C+D%2E+Papailiopoulos%2C+and+K%2E+Lee%2E+Lift%3A+Language%2Dinterfaced+fine%2Dtuning+for+non%2Dlanguage+machine+learning+tasks%2E+Advances+in+Neural+Inf)
12. G. A. for Developers. Context caching guide, 2024. gemini-api/docs/caching . URL [https://ai.google.dev/](https://ai.google.dev/) [↗](https://ai.google.dev/)
13. Y. Fu, R. Panda, X. Niu, X. Yue, H. Hajishirzi, Y. Kim, and H. Peng. Data Engineering for Scaling Language Models to 128K Context, Feb. 2024. URL http://arxiv.org/abs/2402.10171 . arXiv:2402.10171 [cs]. [↗](http://arxiv.org/abs/2402.10171)
14. S. Garg, D. Tsipras, P. S. Liang, and G. Valiant. What can transformers learn in-context? a case study of simple function classes. Advances in Neural Information Processing Systems, 35: 30583–30598, 2022. [find](https://scholar.google.com/scholar?q=S%2E+Garg%2C+D%2E+Tsipras%2C+P%2E+S%2E+Liang%2C+and+G%2E+Valiant%2E+What+can+transformers+learn+in%2Dcontext%3F+a+case+study+of+simple+function+classes%2E+Advances+in+Neural+Information+Processing+Systems%2C+35%3A+30583%E2%80%9330598%2C+2)
15. G. Gemini Team. Gemini: A family of highly capable multimodal models. arXiv preprint arXiv:2312.11805, 2023. [find](https://scholar.google.com/scholar?q=G%2E+Gemini+Team%2E+Gemini%3A+A+family+of+highly+capable+multimodal+models%2E+arXiv+preprint+arXiv%3A2312%2E11805%2C+2023%2E) [our card](https://md.research.elamur.ai/free/en/papers/gemini-2023-team-gemini-family-highly-capable-multimodal/)
16. G. Gemini Team. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv preprint arxiv:2403.05530, 2024. [find](https://scholar.google.com/scholar?q=G%2E+Gemini+Team%2E+Gemini+1%2E5%3A+Unlocking+multimodal+understanding+across+millions+of+tokens+of+context%2E+arXiv+preprint+arxiv%3A2403%2E05530%2C+2024%2E) [our card](https://md.research.elamur.ai/free/en/papers/gemini-2024-team-gemini-1-5-unlocking-multimodal/)
17. M. Ghallab, A. Howe, C. Knoblock, D. Mcdermott, A. Ram, M. Veloso, D. Weld, and D. Wilkins. PDDL—The Planning Domain Definition Language, 1998. [find](https://scholar.google.com/scholar?q=M%2E+Ghallab%2C+A%2E+Howe%2C+C%2E+Knoblock%2C+D%2E+Mcdermott%2C+A%2E+Ram%2C+M%2E+Veloso%2C+D%2E+Weld%2C+and+D%2E+Wilkins%2E+PDDL%E2%80%94The+Planning+Domain+Definition+Language%2C+1998%2E)
18. N. Goyal, C. Gao, V. Chaudhary, P. Chen, G. Wenzek, D. Ju, S. Krishnan, M. Ranzato, F. Guzmán, and A. Fan. The flores-101 evaluation benchmark for low-resource and multilingual machine translation. Trans. Assoc. Comput. Linguistics, 10:522–538, 2022. [find](https://scholar.google.com/scholar?q=N%2E+Goyal%2C+C%2E+Gao%2C+V%2E+Chaudhary%2C+P%2E+Chen%2C+G%2E+Wenzek%2C+D%2E+Ju%2C+S%2E+Krishnan%2C+M%2E+Ranzato%2C+F%2E+Guzm%C3%A1n%2C+and+A%2E+Fan%2E+The+flores%2D101+evaluation+benchmark+for+low%2Dresource+and+multilingual+machine+translation%2E+Tr)
19. C. Gulcehre, T. L. Paine, S. Srinivasan, K. Konyushkova, L. Weerts, A. Sharma, A. Siddhant, A. Ahern, M. Wang, C. Gu, et al. Reinforced self-training (rest) for language modeling. arXiv preprint arXiv:2308.08998, 2023. [find](https://scholar.google.com/scholar?q=C%2E+Gulcehre%2C+T%2E+L%2E+Paine%2C+S%2E+Srinivasan%2C+K%2E+Konyushkova%2C+L%2E+Weerts%2C+A%2E+Sharma%2C+A%2E+Siddhant%2C+A%2E+Ahern%2C+M%2E+Wang%2C+C%2E+Gu%2C+et+al%2E+Reinforced+self%2Dtraining+%28rest%29+for+language+modeling%2E+arXiv+preprint+arXiv) [our card](https://md.research.elamur.ai/free/en/papers/gulcehre-2023-reinforced-self-training-rest-language/)
20. T. Hasan, A. Bhattacharjee, M. S. Islam, K. S. Mubasshir, Y. Li, Y. Kang, M. S. Rahman, and R. Shahriyar. Xl-sum: Large-scale multilingual abstractive summarization for 44 languages. In C. Zong, F. Xia, W. Li, and R. Navigli, editors, Findings of the Association for Computational Linguistics: ACL/IJ… [find](https://scholar.google.com/scholar?q=T%2E+Hasan%2C+A%2E+Bhattacharjee%2C+M%2E+S%2E+Islam%2C+K%2E+S%2E+Mubasshir%2C+Y%2E+Li%2C+Y%2E+Kang%2C+M%2E+S%2E+Rahman%2C+and+R%2E+Shahriyar%2E+Xl%2Dsum%3A+Large%2Dscale+multilingual+abstractive+summarization+for+44+languages%2E+In+C%2E+Zong%2C+F%2E+Xi)
21. M. Helmert. The fast downward planning system. Journal of Artificial Intelligence Research, 26: 191–246, July 2006. ISSN 1076-9757. doi: 10.1613/jair.1705. URL http://dx.doi.org/ 10.1613/jair.1705 . [find](https://scholar.google.com/scholar?q=M%2E+Helmert%2E+The+fast+downward+planning+system%2E+Journal+of+Artificial+Intelligence+Research%2C+26%3A+191%E2%80%93246%2C+July+2006%2E+ISSN+1076%2D9757%2E+doi%3A+10%2E1613%2Fjair%2E1705%2E+URL+http%3A%2F%2Fdx%2Edoi%2Eorg%2F+10%2E1613%2Fjair%2E1705+%2E)
22. R. Hendel, M. Geva, and A. Globerson. In-context learning creates task vectors. arXiv preprint arXiv:2310.15916, 2023. [find](https://scholar.google.com/scholar?q=R%2E+Hendel%2C+M%2E+Geva%2C+and+A%2E+Globerson%2E+In%2Dcontext+learning+creates+task+vectors%2E+arXiv+preprint+arXiv%3A2310%2E15916%2C+2023%2E)
23. D. Hendrycks, C. Burns, S. Kadavath, A. Arora, S. Basart, E. Tang, D. Song, and J. Steinhardt. Measuring mathematical problem solving with the math dataset. arXiv preprint arXiv:2103.03874, 2021. [find](https://scholar.google.com/scholar?q=D%2E+Hendrycks%2C+C%2E+Burns%2C+S%2E+Kadavath%2C+A%2E+Arora%2C+S%2E+Basart%2C+E%2E+Tang%2C+D%2E+Song%2C+and+J%2E+Steinhardt%2E+Measuring+mathematical+problem+solving+with+the+math+dataset%2E+arXiv+preprint+arXiv%3A2103%2E03874%2C+2021%2E) [our card](https://md.research.elamur.ai/free/en/papers/hendrycks-2021-measuring-mathematical-problem-solving-math/)
24. A. Hosseini, X. Yuan, N. Malkin, A. Courville, A. Sordoni, and R. Agarwal. V-star: Training verifiers for self-taught reasoners. arXiv preprint arXiv:2402.06457, 2024. [find](https://scholar.google.com/scholar?q=A%2E+Hosseini%2C+X%2E+Yuan%2C+N%2E+Malkin%2C+A%2E+Courville%2C+A%2E+Sordoni%2C+and+R%2E+Agarwal%2E+V%2Dstar%3A+Training+verifiers+for+self%2Dtaught+reasoners%2E+arXiv+preprint+arXiv%3A2402%2E06457%2C+2024%2E) [our card](https://md.research.elamur.ai/free/en/papers/hosseini-2024-v-star-training-verifiers-self/)
25. H. J. Jeon, J. D. Lee, Q. Lei, and B. Van Roy. An information-theoretic analysis of in-context learning. arXiv preprint arXiv:2401.15530, 2024. — [arXiv:2401.15530](https://arxiv.org/abs/2401.15530) [find](https://scholar.google.com/scholar?q=H%2E+J%2E+Jeon%2C+J%2E+D%2E+Lee%2C+Q%2E+Lei%2C+and+B%2E+Van+Roy%2E+An+information%2Dtheoretic+analysis+of+in%2Dcontext+learning%2E+arXiv+preprint+arXiv%3A2401%2E15530%2C+2024%2E+%E2%80%94+%5BarXiv%3A2401%2E15530%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2401%2E15530%29)
26. G. Kamradt. LLMTest_NeedleInAHaystack. [https://github.com/gkamradt/LLMTest_](https://github.com/gkamradt/LLMTest_) NeedleInAHaystack , 2023. Accessed: 2024-04-16. [↗](https://github.com/gkamradt/LLMTest_)
27. J. Kaplan, S. McCandlish, T. Henighan, T. B. Brown, B. Chess, R. Child, S. Gray, A. Radford, J. Wu, and D. Amodei. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361, 2020. [find](https://scholar.google.com/scholar?q=J%2E+Kaplan%2C+S%2E+McCandlish%2C+T%2E+Henighan%2C+T%2E+B%2E+Brown%2C+B%2E+Chess%2C+R%2E+Child%2C+S%2E+Gray%2C+A%2E+Radford%2C+J%2E+Wu%2C+and+D%2E+Amodei%2E+Scaling+laws+for+neural+language+models%2E+arXiv+preprint+arXiv%3A2001%2E08361%2C+2020%2E)
28. O. Khattab, A. Singhvi, P. Maheshwari, Z. Zhang, K. Santhanam, S. V. A, S. Haq, A. Sharma, T. T. Joshi, H. Moazam, H. Miller, M. Zaharia, and C. Potts. DSPy: Compiling declarative language model calls into state-of-the-art pipelines. In The Twelfth International Conference on Learning Representation… [find](https://scholar.google.com/scholar?q=O%2E+Khattab%2C+A%2E+Singhvi%2C+P%2E+Maheshwari%2C+Z%2E+Zhang%2C+K%2E+Santhanam%2C+S%2E+V%2E+A%2C+S%2E+Haq%2C+A%2E+Sharma%2C+T%2E+T%2E+Joshi%2C+H%2E+Moazam%2C+H%2E+Miller%2C+M%2E+Zaharia%2C+and+C%2E+Potts%2E+DSPy%3A+Compiling+declarative+language+model+calls)
29. H. J. Kim, H. Cho, J. Kim, T. Kim, K. M. Yoo, and S. Lee. Self-generated in-context learning: Leveraging auto-regressive language models as a demonstration generator. CoRR, abs/2206.08082, 2022. doi: 10.48550/ARXIV.2206.08082. URL https://doi.org/10.48550/arXiv.2206. 08082 . — [doi:10.48550/arxiv.2206.08082](https://doi.org/10.48550/arxiv.2206.08082) [↗](https://doi.org/10.48550/arXiv.2206)
30. J. Kossen, Y. Gal, and T. Rainforth. In-context learning learns label relationships but is not conventional learning. In The Twelfth International Conference on Learning Representations, 2023. [find](https://scholar.google.com/scholar?q=J%2E+Kossen%2C+Y%2E+Gal%2C+and+T%2E+Rainforth%2E+In%2Dcontext+learning+learns+label+relationships+but+is+not+conventional+learning%2E+In+The+Twelfth+International+Conference+on+Learning+Representations%2C+2023%2E)
31. M. Li, S. Gong, J. Feng, Y. Xu, J. Zhang, Z. Wu, and L. Kong. In-context learning with many demonstration examples. CoRR, abs/2302.04931, 2023. doi: 10.48550/ARXIV.2302.04931. URL https://doi.org/10.48550/arXiv.2302.04931 . — [doi:10.48550/arxiv.2302.04931](https://doi.org/10.48550/arxiv.2302.04931) [↗](https://doi.org/10.48550/arXiv.2302.04931)
32. R. Li, G. Wang, and J. Li. Are human-generated demonstrations necessary for in-context learning? In The Twelfth International Conference on Learning Representations, 2024. URL [https://openreview.net/forum?id=frRDT6EOhg](https://openreview.net/forum?id=frRDT6EOhg) . [↗](https://openreview.net/forum?id=frRDT6EOhg)
33. H. Lightman, V. Kosaraju, Y. Burda, H. Edwards, B. Baker, T. Lee, J. Leike, J. Schulman, I. Sutskever, and K. Cobbe. Let’s verify step by step. CoRR, abs/2305.20050, 2023. doi: 10.48550/ARXIV.2305.20050. URL https://doi.org/10.48550/arXiv.2305.20050 . [↗](https://doi.org/10.48550/arXiv.2305.20050) [our card](https://md.research.elamur.ai/free/en/papers/lightman-2023-let-s-verify-step-step/)
34. B. Y. Lin, A. Ravichander, X. Lu, N. Dziri, M. Sclar, K. Chandu, C. Bhagavatula, and Y. Choi. The unlocking spell on base llms: Rethinking alignment via in-context learning. arXiv preprint arXiv:2312.01552, 2023. [find](https://scholar.google.com/scholar?q=B%2E+Y%2E+Lin%2C+A%2E+Ravichander%2C+X%2E+Lu%2C+N%2E+Dziri%2C+M%2E+Sclar%2C+K%2E+Chandu%2C+C%2E+Bhagavatula%2C+and+Y%2E+Choi%2E+The+unlocking+spell+on+base+llms%3A+Rethinking+alignment+via+in%2Dcontext+learning%2E+arXiv+preprint+arXiv%3A2312%2E) [our card](https://md.research.elamur.ai/free/en/papers/lin-2023-unlocking-spell-base-llms-rethinking/)
35. C.-Y. Lin. ROUGE: A package for automatic evaluation of summaries. In Text Summarization Branches Out, pages 74–81, Barcelona, Spain, July 2004. Association for Computational Linguistics. URL https://aclanthology.org/W04-1013 . [↗](https://aclanthology.org/W04-1013)
36. Z. Lin and K. Lee. Dual operating modes of in-context learning. arXiv preprint arXiv:2402.18819, 2024. — [arXiv:2402.18819](https://arxiv.org/abs/2402.18819) [find](https://scholar.google.com/scholar?q=Z%2E+Lin+and+K%2E+Lee%2E+Dual+operating+modes+of+in%2Dcontext+learning%2E+arXiv+preprint+arXiv%3A2402%2E18819%2C+2024%2E+%E2%80%94+%5BarXiv%3A2402%2E18819%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2402%2E18819%29)
37. H. Liu, D. Tam, M. Muqeeth, J. Mohta, T. Huang, M. Bansal, and C. A. Raffel. Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning. Advances in Neural Information Processing Systems, 35:1950–1965, 2022. [find](https://scholar.google.com/scholar?q=H%2E+Liu%2C+D%2E+Tam%2C+M%2E+Muqeeth%2C+J%2E+Mohta%2C+T%2E+Huang%2C+M%2E+Bansal%2C+and+C%2E+A%2E+Raffel%2E+Few%2Dshot+parameter%2Defficient+fine%2Dtuning+is+better+and+cheaper+than+in%2Dcontext+learning%2E+Advances+in+Neural+Information+Pro) [our card](https://md.research.elamur.ai/free/en/papers/liu-2022-few-shot-parameter-efficient-fine/)
38. Y. Lu, M. Bartolo, A. Moore, S. Riedel, and P. Stenetorp. Fantastically ordered prompts and where to find them: Overcoming few-shot prompt order sensitivity. arXiv preprint arXiv:2104.08786, 2021. [find](https://scholar.google.com/scholar?q=Y%2E+Lu%2C+M%2E+Bartolo%2C+A%2E+Moore%2C+S%2E+Riedel%2C+and+P%2E+Stenetorp%2E+Fantastically+ordered+prompts+and+where+to+find+them%3A+Overcoming+few%2Dshot+prompt+order+sensitivity%2E+arXiv+preprint+arXiv%3A2104%2E08786%2C+2021%2E) [our card](https://md.research.elamur.ai/free/en/papers/lu-2022-fantastically-ordered-prompts-where-find/)
39. Y. Lu, M. Bartolo, A. Moore, S. Riedel, and P. Stenetorp. Fantastically ordered prompts and where to find them: Overcoming few-shot prompt order sensitivity. In S. Muresan, P. Nakov, and A. Villavicencio, editors, Proceedings of the 60th Annual Meeting of the Association for Computational Linguistic… [find](https://scholar.google.com/scholar?q=Y%2E+Lu%2C+M%2E+Bartolo%2C+A%2E+Moore%2C+S%2E+Riedel%2C+and+P%2E+Stenetorp%2E+Fantastically+ordered+prompts+and+where+to+find+them%3A+Overcoming+few%2Dshot+prompt+order+sensitivity%2E+In+S%2E+Muresan%2C+P%2E+Nakov%2C+and+A%2E+Villavicen) [our card](https://md.research.elamur.ai/free/en/papers/lu-2022-fantastically-ordered-prompts-where-find/)
40. P. Malo, A. Sinha, P. Korhonen, J. Wallenius, and P. Takala. Good debt or bad debt: Detecting semantic orientations in economic texts. Journal of the Association for Information Science and Technology, 65(4):782–796, 2014. [find](https://scholar.google.com/scholar?q=P%2E+Malo%2C+A%2E+Sinha%2C+P%2E+Korhonen%2C+J%2E+Wallenius%2C+and+P%2E+Takala%2E+Good+debt+or+bad+debt%3A+Detecting+semantic+orientations+in+economic+texts%2E+Journal+of+the+Association+for+Information+Science+and+Technology)
41. S. Min, X. Lyu, A. Holtzman, M. Artetxe, M. Lewis, H. Hajishirzi, and L. Zettlemoyer. Rethinking the role of demonstrations: What makes in-context learning work? In Y. Goldberg, Z. Kozareva, and Y. Zhang, editors, Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing… [find](https://scholar.google.com/scholar?q=S%2E+Min%2C+X%2E+Lyu%2C+A%2E+Holtzman%2C+M%2E+Artetxe%2C+M%2E+Lewis%2C+H%2E+Hajishirzi%2C+and+L%2E+Zettlemoyer%2E+Rethinking+the+role+of+demonstrations%3A+What+makes+in%2Dcontext+learning+work%3F+In+Y%2E+Goldberg%2C+Z%2E+Kozareva%2C+and+Y%2E+Zh) [our card](https://md.research.elamur.ai/free/en/papers/min-2022-rethinking-role-demonstrations-what-makes/)
42. M. Mosbach, T. Pimentel, S. Ravfogel, D. Klakow, and Y. Elazar. Few-shot fine-tuning vs. in-context learning: A fair comparison and evaluation. arXiv preprint arXiv:2305.16938, 2023. [find](https://scholar.google.com/scholar?q=M%2E+Mosbach%2C+T%2E+Pimentel%2C+S%2E+Ravfogel%2C+D%2E+Klakow%2C+and+Y%2E+Elazar%2E+Few%2Dshot+fine%2Dtuning+vs%2E+in%2Dcontext+learning%3A+A+fair+comparison+and+evaluation%2E+arXiv+preprint+arXiv%3A2305%2E16938%2C+2023%2E)
43. S. Narayan, S. B. Cohen, and M. Lapata. Don’t give me the details, just the summary! topic-aware convolutional neural networks for extreme summarization. In E. Riloff, D. Chiang, J. Hockenmaier, and J. Tsujii, editors, Proceedings of the 2018 Conference on Empirical Methods in Natural Language Proce… [find](https://scholar.google.com/scholar?q=S%2E+Narayan%2C+S%2E+B%2E+Cohen%2C+and+M%2E+Lapata%2E+Don%E2%80%99t+give+me+the+details%2C+just+the+summary%21+topic%2Daware+convolutional+neural+networks+for+extreme+summarization%2E+In+E%2E+Riloff%2C+D%2E+Chiang%2C+J%2E+Hockenmaier%2C+and+J)
44. A. Ni, S. Iyer, D. Radev, V. Stoyanov, W.-t. Yih, S. Wang, and X. V. Lin. Lever: Learning to verify language-to-code generation with execution. In International Conference on Machine Learning, pages 26106–26128. PMLR, 2023. [find](https://scholar.google.com/scholar?q=A%2E+Ni%2C+S%2E+Iyer%2C+D%2E+Radev%2C+V%2E+Stoyanov%2C+W%2E%2Dt%2E+Yih%2C+S%2E+Wang%2C+and+X%2E+V%2E+Lin%2E+Lever%3A+Learning+to+verify+language%2Dto%2Dcode+generation+with+execution%2E+In+International+Conference+on+Machine+Learning%2C+pages+2) [our card](https://md.research.elamur.ai/free/en/papers/ni-2023-lever-learning-verify-language-code/)
45. M. A. NLLB Team. No language left behind: Scaling human-centered machine translation. arXiv preprint, 2022. [find](https://scholar.google.com/scholar?q=M%2E+A%2E+NLLB+Team%2E+No+language+left+behind%3A+Scaling+human%2Dcentered+machine+translation%2E+arXiv+preprint%2C+2022%2E)
46. C. Olsson, N. Elhage, N. Nanda, N. Joseph, N. DasSarma, T. Henighan, B. Mann, A. Askell, Y. Bai, A. Chen, T. Conerly, D. Drain, D. Ganguli, Z. Hatfield-Dodds, D. Hernandez, S. Johnston, A. Jones, J. Kernion, L. Lovitt, K. Ndousse, D. Amodei, T. Brown, J. Clark, J. Kaplan, S. McCandlish, and C. Olah.… [find](https://scholar.google.com/scholar?q=C%2E+Olsson%2C+N%2E+Elhage%2C+N%2E+Nanda%2C+N%2E+Joseph%2C+N%2E+DasSarma%2C+T%2E+Henighan%2C+B%2E+Mann%2C+A%2E+Askell%2C+Y%2E+Bai%2C+A%2E+Chen%2C+T%2E+Conerly%2C+D%2E+Drain%2C+D%2E+Ganguli%2C+Z%2E+Hatfield%2DDodds%2C+D%2E+Hernandez%2C+S%2E+Johnston%2C+A%2E+Jones%2C+J%2E+K)
47. J. Pan. What in-context learning “learns” in-context: Disentangling task recognition and task learning. PhD thesis, Princeton University, 2023. [find](https://scholar.google.com/scholar?q=J%2E+Pan%2E+What+in%2Dcontext+learning+%E2%80%9Clearns%E2%80%9D+in%2Dcontext%3A+Disentangling+task+recognition+and+task+learning%2E+PhD+thesis%2C+Princeton+University%2C+2023%2E)
48. F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, et al. Scikit-learn: Machine learning in python. the Journal of machine Learning research, 12:2825–2830, 2011. [find](https://scholar.google.com/scholar?q=F%2E+Pedregosa%2C+G%2E+Varoquaux%2C+A%2E+Gramfort%2C+V%2E+Michel%2C+B%2E+Thirion%2C+O%2E+Grisel%2C+M%2E+Blondel%2C+P%2E+Prettenhofer%2C+R%2E+Weiss%2C+V%2E+Dubourg%2C+et+al%2E+Scikit%2Dlearn%3A+Machine+learning+in+python%2E+the+Journal+of+machine+Le)
49. R. Pope, S. Douglas, A. Chowdhery, J. Devlin, J. Bradbury, J. Heek, K. Xiao, S. Agrawal, and J. Dean. Efficiently scaling transformer inference. Proceedings of Machine Learning and Systems, 5, 2023. [find](https://scholar.google.com/scholar?q=R%2E+Pope%2C+S%2E+Douglas%2C+A%2E+Chowdhery%2C+J%2E+Devlin%2C+J%2E+Bradbury%2C+J%2E+Heek%2C+K%2E+Xiao%2C+S%2E+Agrawal%2C+and+J%2E+Dean%2E+Efficiently+scaling+transformer+inference%2E+Proceedings+of+Machine+Learning+and+Systems%2C+5%2C+2023%2E)
50. M. Popović. chrf++: words helping character n-grams. In Proceedings of the second conference on machine translation, pages 612–618, 2017. [find](https://scholar.google.com/scholar?q=M%2E+Popovi%C4%87%2E+chrf%2B%2B%3A+words+helping+character+n%2Dgrams%2E+In+Proceedings+of+the+second+conference+on+machine+translation%2C+pages+612%E2%80%93618%2C+2017%2E) [our card](https://md.research.elamur.ai/free/en/papers/popovic-2017-chrf-words-helping-character-n/)
51. 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. [find](https://scholar.google.com/scholar?q=A%2E+Radford%2C+J%2E+Wu%2C+R%2E+Child%2C+D%2E+Luan%2C+D%2E+Amodei%2C+I%2E+Sutskever%2C+et+al%2E+Language+models+are+unsupervised+multitask+learners%2E+OpenAI+blog%2C+1%288%29%3A9%2C+2019%2E)
52. D. Rein, B. L. Hou, A. C. Stickland, J. Petty, R. Y. Pang, J. Dirani, J. Michael, and S. R. Bowman. Gpqa: A graduate-level google-proof q&a benchmark. arXiv preprint arXiv:2311.12022, 2023. [find](https://scholar.google.com/scholar?q=D%2E+Rein%2C+B%2E+L%2E+Hou%2C+A%2E+C%2E+Stickland%2C+J%2E+Petty%2C+R%2E+Y%2E+Pang%2C+J%2E+Dirani%2C+J%2E+Michael%2C+and+S%2E+R%2E+Bowman%2E+Gpqa%3A+A+graduate%2Dlevel+google%2Dproof+q%26a+benchmark%2E+arXiv+preprint+arXiv%3A2311%2E12022%2C+2023%2E) [our card](https://md.research.elamur.ai/free/en/papers/rein-2023-gpqa-graduate-level-google-proof/)
53. N. R. Robinson, P. Ogayo, D. R. Mortensen, and G. Neubig. Chatgpt mt: Competitive for high-(but not low-) resource languages. arXiv preprint arXiv:2309.07423, 2023. [find](https://scholar.google.com/scholar?q=N%2E+R%2E+Robinson%2C+P%2E+Ogayo%2C+D%2E+R%2E+Mortensen%2C+and+G%2E+Neubig%2E+Chatgpt+mt%3A+Competitive+for+high%2D%28but+not+low%2D%29+resource+languages%2E+arXiv+preprint+arXiv%3A2309%2E07423%2C+2023%2E) [our card](https://md.research.elamur.ai/free/en/papers/robinson-2023-chatgpt-mt-competitive-high-but/)
54. J. Seipp, Á. Torralba, and J. Hoffmann. PDDL generators. https://doi.org/10.5281/ zenodo.6382173 , 2022. [find](https://scholar.google.com/scholar?q=J%2E+Seipp%2C+%C3%81%2E+Torralba%2C+and+J%2E+Hoffmann%2E+PDDL+generators%2E+https%3A%2F%2Fdoi%2Eorg%2F10%2E5281%2F+zenodo%2E6382173+%2C+2022%2E)
55. A. Singh, J. D. Co-Reyes, R. Agarwal, A. Anand, P. Patil, X. Garcia, P. J. Liu, J. Harrison, J. Lee, K. Xu, A. T. Parisi, A. Kumar, A. A. Alemi, A. Rizkowsky, A. Nova, B. Adlam, B. Bohnet, G. F. Elsayed, H. Sedghi, I. Mordatch, I. Simpson, I. Gur, J. Snoek, J. Pennington, J. Hron, K. Kenealy, K. Swe… [find](https://scholar.google.com/scholar?q=A%2E+Singh%2C+J%2E+D%2E+Co%2DReyes%2C+R%2E+Agarwal%2C+A%2E+Anand%2C+P%2E+Patil%2C+X%2E+Garcia%2C+P%2E+J%2E+Liu%2C+J%2E+Harrison%2C+J%2E+Lee%2C+K%2E+Xu%2C+A%2E+T%2E+Parisi%2C+A%2E+Kumar%2C+A%2E+A%2E+Alemi%2C+A%2E+Rizkowsky%2C+A%2E+Nova%2C+B%2E+Adlam%2C+B%2E+Bohnet%2C+G%2E+F%2E+Elsay) [our card](https://md.research.elamur.ai/free/en/papers/singh-2023-human-data-scaling-self-training/)
56. M. Suzgun, N. Scales, N. Schärli, S. Gehrmann, Y. Tay, H. W. Chung, A. Chowdhery, Q. V. Le, E. H. Chi, D. Zhou, et al. Challenging big-bench tasks and whether chain-of-thought can solve them. arXiv preprint arXiv:2210.09261, 2022. [find](https://scholar.google.com/scholar?q=M%2E+Suzgun%2C+N%2E+Scales%2C+N%2E+Sch%C3%A4rli%2C+S%2E+Gehrmann%2C+Y%2E+Tay%2C+H%2E+W%2E+Chung%2C+A%2E+Chowdhery%2C+Q%2E+V%2E+Le%2C+E%2E+H%2E+Chi%2C+D%2E+Zhou%2C+et+al%2E+Challenging+big%2Dbench+tasks+and+whether+chain%2Dof%2Dthought+can+solve+them%2E+arXiv+pr) [our card](https://md.research.elamur.ai/free/en/papers/suzgun-2023-challenging-big-bench-tasks-whether/)
57. H. Touvron, L. Martin, K. Stone, P. Albert, A. Almahairi, Y. Babaei, N. Bashlykov, S. Batra, P. Bhargava, S. Bhosale, et al. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288, 2023. [find](https://scholar.google.com/scholar?q=H%2E+Touvron%2C+L%2E+Martin%2C+K%2E+Stone%2C+P%2E+Albert%2C+A%2E+Almahairi%2C+Y%2E+Babaei%2C+N%2E+Bashlykov%2C+S%2E+Batra%2C+P%2E+Bhargava%2C+S%2E+Bhosale%2C+et+al%2E+Llama+2%3A+Open+foundation+and+fine%2Dtuned+chat+models%2E+arXiv+preprint+arXiv%3A2)
58. R. Vacareanu, V.-A. Negru, V. Suciu, and M. Surdeanu. From words to numbers: Your large language model is secretly a capable regressor when given in-context examples. arXiv preprint arXiv:2404.07544, 2024. — [arXiv:2404.07544](https://arxiv.org/abs/2404.07544) [find](https://scholar.google.com/scholar?q=R%2E+Vacareanu%2C+V%2E%2DA%2E+Negru%2C+V%2E+Suciu%2C+and+M%2E+Surdeanu%2E+From+words+to+numbers%3A+Your+large+language+model+is+secretly+a+capable+regressor+when+given+in%2Dcontext+examples%2E+arXiv+preprint+arXiv%3A2404%2E07544%2C+)
59. K. Valmeekam, M. Marquez, S. Sreedharan, and S. Kambhampati. On the planning abilities of large language models-a critical investigation. Advances in Neural Information Processing Systems, 36, 2024. [find](https://scholar.google.com/scholar?q=K%2E+Valmeekam%2C+M%2E+Marquez%2C+S%2E+Sreedharan%2C+and+S%2E+Kambhampati%2E+On+the+planning+abilities+of+large+language+models%2Da+critical+investigation%2E+Advances+in+Neural+Information+Processing+Systems%2C+36%2C+2024%2E)
60. J. von Oswald, E. Niklasson, E. Randazzo, J. Sacramento, A. Mordvintsev, A. Zhmoginov, and M. Vladymyrov. Transformers learn in-context by gradient descent, Dec. 2022. URL http://arxiv.org/abs/2212.07677 . arXiv:2212.07677 [cs]. [↗](http://arxiv.org/abs/2212.07677) [our card](https://md.research.elamur.ai/free/en/papers/oswald-2022-transformers-learn-context-gradient-descent/)
61. X. Wang, W. Zhu, M. Saxon, M. Steyvers, and W. Y. Wang. Large language models are latent variable models: Explaining and finding good demonstrations for in-context learning. Advances in Neural Information Processing Systems, 36, 2024. [find](https://scholar.google.com/scholar?q=X%2E+Wang%2C+W%2E+Zhu%2C+M%2E+Saxon%2C+M%2E+Steyvers%2C+and+W%2E+Y%2E+Wang%2E+Large+language+models+are+latent+variable+models%3A+Explaining+and+finding+good+demonstrations+for+in%2Dcontext+learning%2E+Advances+in+Neural+Informa)
62. J. Wei, X. Wang, D. Schuurmans, M. Bosma, F. Xia, E. Chi, Q. V. Le, D. Zhou, et al. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35:24824–24837, 2022. [find](https://scholar.google.com/scholar?q=J%2E+Wei%2C+X%2E+Wang%2C+D%2E+Schuurmans%2C+M%2E+Bosma%2C+F%2E+Xia%2C+E%2E+Chi%2C+Q%2E+V%2E+Le%2C+D%2E+Zhou%2C+et+al%2E+Chain%2Dof%2Dthought+prompting+elicits+reasoning+in+large+language+models%2E+Advances+in+neural+information+processing+sys) [our card](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/)
63. J. Wei, J. Wei, Y. Tay, D. Tran, A. Webson, Y. Lu, X. Chen, H. Liu, D. Huang, D. Zhou, et al. Larger language models do in-context learning differently. arXiv preprint arXiv:2303.03846, 2023. [find](https://scholar.google.com/scholar?q=J%2E+Wei%2C+J%2E+Wei%2C+Y%2E+Tay%2C+D%2E+Tran%2C+A%2E+Webson%2C+Y%2E+Lu%2C+X%2E+Chen%2C+H%2E+Liu%2C+D%2E+Huang%2C+D%2E+Zhou%2C+et+al%2E+Larger+language+models+do+in%2Dcontext+learning+differently%2E+arXiv+preprint+arXiv%3A2303%2E03846%2C+2023%2E) [our card](https://md.research.elamur.ai/free/en/papers/wei-2023-larger-language-models-context-learning/)
64. H. Wu and K. Tu. Layer-condensed kv cache for efficient inference of large language models. arXiv preprint arXiv:2405.10637, 2024. [find](https://scholar.google.com/scholar?q=H%2E+Wu+and+K%2E+Tu%2E+Layer%2Dcondensed+kv+cache+for+efficient+inference+of+large+language+models%2E+arXiv+preprint+arXiv%3A2405%2E10637%2C+2024%2E)
65. Y. Xiang, H. Yan, L. Gui, and Y. He. Addressing order sensitivity of in-context demonstration examples in causal language models. arXiv preprint arXiv:2402.15637, 2024. [find](https://scholar.google.com/scholar?q=Y%2E+Xiang%2C+H%2E+Yan%2C+L%2E+Gui%2C+and+Y%2E+He%2E+Addressing+order+sensitivity+of+in%2Dcontext+demonstration+examples+in+causal+language+models%2E+arXiv+preprint+arXiv%3A2402%2E15637%2C+2024%2E)
66. S. M. Xie, A. Raghunathan, P. Liang, and T. Ma. An explanation of in-context learning as implicit bayesian inference. arXiv preprint arXiv:2111.02080, 2021. [find](https://scholar.google.com/scholar?q=S%2E+M%2E+Xie%2C+A%2E+Raghunathan%2C+P%2E+Liang%2C+and+T%2E+Ma%2E+An+explanation+of+in%2Dcontext+learning+as+implicit+bayesian+inference%2E+arXiv+preprint+arXiv%3A2111%2E02080%2C+2021%2E) [our card](https://md.research.elamur.ai/free/en/papers/xie-2021-explanation-context-learning-implicit-bayesian/)
67. Y. Xing, X. Lin, N. Suh, Q. Song, and G. Cheng. Benefits of transformer: In-context learning in linear regression tasks with unstructured data. arXiv preprint arXiv:2402.00743, 2024. — [arXiv:2402.00743](https://arxiv.org/abs/2402.00743) [find](https://scholar.google.com/scholar?q=Y%2E+Xing%2C+X%2E+Lin%2C+N%2E+Suh%2C+Q%2E+Song%2C+and+G%2E+Cheng%2E+Benefits+of+transformer%3A+In%2Dcontext+learning+in+linear+regression+tasks+with+unstructured+data%2E+arXiv+preprint+arXiv%3A2402%2E00743%2C+2024%2E+%E2%80%94+%5BarXiv%3A2402%2E007)
68. W. Xiong, J. Liu, I. Molybog, H. Zhang, P. Bhargava, R. Hou, L. Martin, R. Rungta, K. A. Sankararaman, B. Oguz, M. Khabsa, H. Fang, Y. Mehdad, S. Narang, K. Malik, A. Fan, S. Bhosale, S. Edunov, M. Lewis, S. Wang, and H. Ma. Effective long-context scaling of foundation models. CoRR, abs/2309.16039,… [find](https://scholar.google.com/scholar?q=W%2E+Xiong%2C+J%2E+Liu%2C+I%2E+Molybog%2C+H%2E+Zhang%2C+P%2E+Bhargava%2C+R%2E+Hou%2C+L%2E+Martin%2C+R%2E+Rungta%2C+K%2E+A%2E+Sankararaman%2C+B%2E+Oguz%2C+M%2E+Khabsa%2C+H%2E+Fang%2C+Y%2E+Mehdad%2C+S%2E+Narang%2C+K%2E+Malik%2C+A%2E+Fan%2C+S%2E+Bhosale%2C+S%2E+Edunov%2C+M%2E+Le) [our card](https://md.research.elamur.ai/free/en/papers/xiong-2023-effective-long-context-scaling-foundation/)
69. K. M. Yoo, J. Kim, H. J. Kim, H. Cho, H. Jo, S. Lee, S. Lee, and T. Kim. Ground-truth labels matter: A deeper look into input-label demonstrations. In Y. Goldberg, Z. Kozareva, and Y. Zhang, editors, Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022,… [find](https://scholar.google.com/scholar?q=K%2E+M%2E+Yoo%2C+J%2E+Kim%2C+H%2E+J%2E+Kim%2C+H%2E+Cho%2C+H%2E+Jo%2C+S%2E+Lee%2C+S%2E+Lee%2C+and+T%2E+Kim%2E+Ground%2Dtruth+labels+matter%3A+A+deeper+look+into+input%2Dlabel+demonstrations%2E+In+Y%2E+Goldberg%2C+Z%2E+Kozareva%2C+and+Y%2E+Zhang%2C+editors%2C+)
70. Z. Yuan, H. Yuan, C. Li, G. Dong, C. Tan, and C. Zhou. Scaling relationship on learning mathematical reasoning with large language models. arXiv preprint arXiv:2308.01825, 2023. [find](https://scholar.google.com/scholar?q=Z%2E+Yuan%2C+H%2E+Yuan%2C+C%2E+Li%2C+G%2E+Dong%2C+C%2E+Tan%2C+and+C%2E+Zhou%2E+Scaling+relationship+on+learning+mathematical+reasoning+with+large+language+models%2E+arXiv+preprint+arXiv%3A2308%2E01825%2C+2023%2E) [our card](https://md.research.elamur.ai/free/en/papers/yuan-2023-scaling-relationship-learning-mathematical-reasoning/)
71. J. Zhang, Y. Zhao, M. Saleh, and P. Liu. Pegasus: Pre-training with extracted gap-sentences for abstractive summarization. In International conference on machine learning, pages 11328–11339. PMLR, 2020. [find](https://scholar.google.com/scholar?q=J%2E+Zhang%2C+Y%2E+Zhao%2C+M%2E+Saleh%2C+and+P%2E+Liu%2E+Pegasus%3A+Pre%2Dtraining+with+extracted+gap%2Dsentences+for+abstractive+summarization%2E+In+International+conference+on+machine+learning%2C+pages+11328%E2%80%9311339%2E+PMLR%2C+202) [our card](https://md.research.elamur.ai/free/en/papers/zhang-2019-pegasus-pre-training-extracted-gap/)
72. R. Zhang, S. Frei, and P. L. Bartlett. Trained transformers learn linear models in-context. arXiv preprint arXiv:2306.09927, 2023. — [arXiv:2306.09927](https://arxiv.org/abs/2306.09927) [find](https://scholar.google.com/scholar?q=R%2E+Zhang%2C+S%2E+Frei%2C+and+P%2E+L%2E+Bartlett%2E+Trained+transformers+learn+linear+models+in%2Dcontext%2E+arXiv+preprint+arXiv%3A2306%2E09927%2C+2023%2E+%E2%80%94+%5BarXiv%3A2306%2E09927%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2306%2E09927%29)
73. Z. Zhang, A. Zhang, M. Li, and A. Smola. Automatic chain of thought prompting in large language models. In The Eleventh International Conference on Learning Representations, 2023. URL [https://openreview.net/forum?id=5NTt8GFjUHkr](https://openreview.net/forum?id=5NTt8GFjUHkr) . [↗](https://openreview.net/forum?id=5NTt8GFjUHkr) [our card](https://md.research.elamur.ai/free/en/papers/zhang-2022-automatic-chain-thought-prompting-large/)
74. L. Zheng, J. Yuan, C. Wang, and L. Kong. Efficient attention via control variates. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net, 2023. URL [https://openreview.net/pdf?id=G-uNfHKrj46](https://openreview.net/pdf?id=G-uNfHKrj46) . [↗](https://openreview.net/pdf?id=G-uNfHKrj46)