Topic summary
AI prompt
Extracted from the Wikipedia article Prompt engineering.
References
- ^ 2026.
- ^ 2026.
- ^ [cs.CL].
- ^ [cs.CL].
- ^
- ^ 2026.
- ^ . OpenAI. Archived(PDF) from the original on February 6, 2021 2023.
We demonstrate language models can perform down-stream tasks in a zero-shot setting – without any parameter or architecture modification
- ^ 2025.
- ^ 11033. arXiv:2406.19898. doi:10.18653/v1/2024.emnlp-main.617.
- ^ 2023.
- ^ 2023.
Next, I gave a more complicated prompt to attempt to throw MusicGen for a loop: "Lo-fi slow BPM electro chill with organic samples."
- ^ 2025.
- ^ .
- ^ .
- ^ 2025.
- ^ [cs.CL].
- ^ 'Vibe coding' named Collins Dictionary's Word of the Year". CNN. Archived from the original on November 14, 2025 2026.
- ^ 2025.
- ^ 2025.
- ^ [cs.CL].
- ^ .
In prompting, a pre-trained language model is given a prompt (e.g. a natural language instruction) of a task and completes the response without any further training or gradient updates to its parameters... The ability to perform a task via few-shot prompting is emergent when a model has random performance until a certain scale, after which performance increases to well-above random
- ^ .
- ^ 2023.
By the time you type a query into ChatGPT, the network should be fixed; unlike humans, it should not continue to learn. So it came as a surprise that LLMs do, in fact, learn from their users' prompts—an ability known as in-context learning.
- ^ .
Training a model to perform in-context learning can be viewed as an instance of the more general learning-to-learn or meta-learning paradigm
- ^ .
- ^ 9232. arXiv:2311.01967. doi:10.18653/v1/2023.findings-emnlp.618. Archived from the original on December 13, 2024 2024.
- ^ 3655. arXiv:2404.01992. doi:10.18653/v1/2024.naacl-long.201. Archived from the original on November 3, 2024 2024.
- ^ .
- ^ 1901. arXiv:2005.14165.
- ^ . ACM Comput. Surv. 53 (3): 63:1–63:34. doi:10.1145/3386252. ISSN 0360-0300.
- ^ .
- ^ 2023.
- ^ 2023.
- ^ 2023.
- ^ . Journal of Machine Learning Research. 2024. Archived(PDF) from the original on May 8, 2025 2025.
- ^ 2023.
- ^ .
- ^ [cs.CL].
- ^ [cs.LG].
- ^ .
- ^ .
- ^ 2025.
- ^ 2025.
- ^ 2023.
- ^ 2023.
- ^ . Archived(PDF) from the original on March 30, 2023 2023.
Prompt engineering is the process of structuring words that can be interpreted and understood by a text-to-image model. Think of it as the language you need to speak in order to tell an AI model what to draw.
- ^ 2023.
- ^ 2025.
- ^ .
Using only 3-5 images of a user-provided concept, like an object or a style, we learn to represent it through new "words" in the embedding space of a frozen text-to-image model.
- ^ . ICCV. 2023. Archived(PDF) from the original on April 28, 2025 2025.
- ^ 7159. doi:10.1007/s00146-026-03093-8. ISSN 1435-5655.
- ^
- ^ 2026.
- ^ [cs.AI].
- ^ 2025.
- ^ 2024
- ^ 2025.
- ^ .
- ^ . BlackboxNLP Workshop. 2023. arXiv:2210.01848. Archived(PDF) from the original on May 9, 2025 2025.
- ^ .
- ^ 7968. arXiv:2305.03495. doi:10.18653/v1/2023.emnlp-main.494. Archived from the original on April 27, 2025 2025.
- ^ .
- ^ . doi:10.18653/v1/2024.emnlp-main.525.
- ^ [cs.CL].
- ^ [cs.CL].
- ^ 2025.
- ^ 4597. doi:10.18653/V1/2021.ACL-LONG.353. S2CID 230433941.
In this paper, we propose prefix-tuning, a lightweight alternative to fine-tuning... Prefix-tuning draws inspiration from prompting
- ^ 3059. arXiv:2104.08691. doi:10.18653/V1/2021.EMNLP-MAIN.243. S2CID 233296808.
In this work, we explore "prompt tuning," a simple yet effective mechanism for learning "soft prompts"...Unlike the discrete text prompts used by GPT-3, soft prompts are learned through back-propagation
- ^ 4235. doi:10.18653/v1/2020.emnlp-main.346. S2CID 226222232. Archived from the original on June 11, 2023 2023.
- ^ 2026.
- ^ .
- ^ . ISSN 2666-920X.
- ^ 2025.
- ^ 2025.
- ^ 2025.
- ^ 2023.
- ^ . The New York Times. ISSN 0362-4331. Archived from the original on August 14, 2023 2023.
- ^ 7736. arXiv:2310.08129. doi:10.1109/cvpr52733.2024.00738. ISBN .
- ^ 2023.
- ^ 2025.