Prompt engineering

Last updated

Prompt engineering is the process of structuring natural language inputs (known as prompts) to produce specified outputs from a generative artificial intelligence (GenAI) model. Context engineering is the related area of software engineering that focuses on the management of non-prompt contexts supplied to the GenAI model, such as metadata, API tools, and tokens.

Contents

During the 2020s AI boom, prompt engineering became regarded as an important business capability across corporations and industries. Employees with the title prompt engineer were hired to create prompts that would increase productivity and efficacy, although the individual title has since lost traction in light of AI models that produce better prompts than humans and corporate training in prompting for general employees.

Common prompting techniques include multi-shot, chain-of-thought, and tree-of-thought prompting, as well as the use of assigning roles to the model. Automated prompt generation methods, such as retrieval-augmented generation (RAG), provide for greater accuracy and a wider scope of functions for prompt engineers. Prompt injection is a type of cybersecurity attack that targets machine learning models through malicious prompts.

Terminology

The Oxford English Dictionary defines prompt engineering as "The action or process of formulating and refining prompts for an artificial intelligence program, algorithm, etc., in order to optimize its output or to achieve a desired outcome; the discipline or profession concerned with this." [1] In 2023, prompt ("an instruction given to an artificial intelligence program, algorithm, etc., which determines or influences the content it generates") was the runner-up to Oxford's word of the year. [2]

Prompt

A prompt is some natural language text that describes and prescribes the task that an artificial intelligence (AI) should perform. [3] A prompt for a text-to-text language model can be a query, a command, or a longer statement referencing context, instructions, and conversation history. The process of prompt engineering may involve designing clear queries, refining wording, providing relevant context, specifying the style of output, and assigning a character for the AI to mimic in order to guide the model toward more accurate, useful, and consistent responses. [4] [5]

When communicating with a text-to-image or a text-to-audio model, a typical prompt contains a description of a desired output such as "a high-quality photo of an astronaut riding a horse" [6] or "Lo-fi slow BPM electro chill with organic samples". [7] Prompt engineering may be applied to text-to-image models to achieve a desired subject, style, layout, lighting, and aesthetic. [8]

Techniques

Common terms used to describe various specific prompt engineering techniques include chain-of-thought, [9] tree-of-thought, [10] and retrieval-augmented generation (RAG). [11] A 2024 survey of the field identified over 50 distinct text-based prompting techniques, 40 multimodal variants, and a vocabulary of 33 terms used across prompting research, highlighting a present lack of standardised terminology for prompt engineering. [12]

Vibe coding is an AI-assisted software development method where a user prompts an LLM with a description of what they want and lets it generate or edit the code. In 2025, "vibe coding" was the Collins Dictionary word of the year. [13]

Context engineering

Context engineering is a related process that focuses on the context elements that accompany user prompts, which include system instructions, retrieved knowledge, tool definitions, conversation summaries, and task metadata. Context engineering is performed to improve reliability, provenance and token efficiency in production LLM systems. [14] [15] The concept emphasises operational practices such as token budgeting, provenance tags, versioning of context artifacts, observability (logging which context was supplied), and context regression tests to ensure that changes to supplied context do not silently alter system behaviour. [16]

Rationale

Research has found that the performance of large language models (LLMs) is highly sensitive to choices such as the ordering of examples, the quality of demonstration labels, and even small variations in phrasing. In some cases, reordering examples in a prompt produced accuracy shifts of more than 40 percent. [12]

In-context learning

A model's ability to temporarily learn from prompts is known as in-context learning. In-context learning is an emergent ability [17] of large language models. It is an emergent property of model scale, meaning that breaks in scaling laws occur, leading to its efficacy increasing at a different rate in larger models than in smaller models. [17] [18] Unlike training and fine-tuning, which produce lasting changes, in-context learning is temporary. [19] Training models to perform in-context learning can be viewed as a form of meta-learning, or "learning to learn". [20]

Prompting to estimate model sensitivity

Research consistently demonstrates that LLMs are highly sensitive to subtle variations in prompt formatting, structure, and linguistic properties. Some studies have shown up to 76 accuracy points across formatting changes in few-shot settings. [21] Linguistic features significantly influence prompt effectiveness—such as morphology, syntax, and lexico-semantic changes—which meaningfully enhance task performance across a variety of tasks. [5] [22] Clausal syntax, for example, improves consistency and reduces uncertainty in knowledge retrieval. [23] This sensitivity persists even with larger model sizes, additional few-shot examples, or instruction tuning.

To address sensitivity of models and make them more robust, several evaluative methods have been proposed. FormatSpread facilitates systematic analysis by evaluating a range of plausible prompt formats, offering a more comprehensive performance interval. [21] Similarly, PromptEval estimates performance distributions across diverse prompts, enabling robust metrics such as performance quantiles and accurate evaluations under constrained budgets. [24]

Prompting techniques

Multi-shot

A prompt may include a few examples for a model to learn from in context, an approach called few-shot learning. [25] [9] For example, the prompt may ask the model to complete "maison→ house, chat→ cat, chien→", with the expected response being dog. [26]

Chain-of-thought

Chain-of-thought (CoT) prompting is a technique that allows large language models (LLMs) to solve a problem as a series of intermediate steps before giving a final answer. In 2022, Google Brain reported that chain-of-thought prompting improves reasoning ability by inducing the model to answer a multi-step problem with steps of reasoning that mimic a train of thought. [9] [27] Chain-of-thought techniques were developed to help LLMs handle multi-step reasoning tasks, such as arithmetic or commonsense reasoning questions. [28] [29]

When applied to PaLM, a 540 billion parameter language model, according to Google, CoT prompting significantly aided the model, allowing it to perform comparably with task-specific fine-tuned models on several tasks, achieving state-of-the-art results at the time on the GSM8K mathematical reasoning benchmark. [9] It is possible to fine-tune models on CoT reasoning datasets to enhance this capability further and stimulate better interpretability. [30] [31]

As originally proposed by Google, [9] each CoT prompt is accompanied by a set of input/output examples—called exemplars—to demonstrate the desired model output, making it a few-shot prompting technique. However, according to a later paper from researchers at Google and the University of Tokyo, simply appending the words "Let's think step-by-step" [32] was also effective, which allowed for CoT to be employed as a zero-shot technique.

Self-consistency

Self-consistency performs several chain-of-thought rollouts, then selects the most commonly reached conclusion out of all the rollouts. [33] [34]

Tree-of-thought

Tree-of-thought prompting generalizes chain-of-thought by generating multiple lines of reasoning in parallel, with the ability to backtrack or explore other paths. It can use tree search algorithms like breadth-first, depth-first, or beam. [10]

Text-to-image prompting

In 2022, text-to-image models like DALL-E 2, Stable Diffusion, and Midjourney were released to the public. These models take text prompts as input and use them to generate images. [35] [8] Early text-to-image models typically do not understand negation, grammar and sentence structure in the same way as large language models, and may thus require a different set of prompting techniques. The prompt "a party with no cake" may produce an image including a cake. [36]

Algorithmically-generated landscape artwork of forest with Shinto shrine.png
Algorithmically-generated landscape artwork of forest with Shinto shrine using negative prompt for green trees.png
Algorithmically-generated landscape artwork of forest with Shinto shrine using negative prompt for round stones.png
Demonstration of the effect of negative prompts on images generated with Stable Diffusion
  • Top: no negative prompt
  • Centre: "green trees"
  • Bottom: "round stones, round rocks"

A text-to-image prompt commonly includes a description of the subject of the art, the desired medium (such as digital painting or photography), style (such as hyperrealistic or pop-art), lighting (such as rim lighting or crepuscular rays), color, and texture. [37] Word order also affects the output of a text-to-image prompt. Words closer to the start of a prompt may be emphasized more heavily. [38]

Artist styles

Some text-to-image models are capable of imitating the style of particular artists by name. For example, the phrase in the style of Greg Rutkowski has been used in Stable Diffusion and Midjourney prompts to generate images in the distinctive style of Polish digital artist Greg Rutkowski. [39] Famous artists such as Vincent van Gogh and Salvador Dalí have also been used for styling and testing. [40]

Textual inversion and embeddings

For text-to-image models, textual inversion performs an optimization process to create a new word embedding based on a set of example images. This embedding vector acts as a "pseudo-word" which can be included in a prompt to express the content or style of the examples. [41]

Image prompting

In 2023, Meta's AI research released Segment Anything, a computer vision model that can perform image segmentation by prompting. As an alternative to text prompts, Segment Anything can accept bounding boxes, segmentation masks, and foreground/background points. [42]

Limitations

The process of writing and refining a prompt for an LLM or generative AI shares some parallels with an iterative engineering design process, such as by discovering reusable best practices through reproducible experimentation. But the techniques that improve performance depend heavily on the specific model being used. Such patterns are also volatile and exhibit significantly different results from seemingly insignificant prompt changes. [43] [44]

Automated prompt generation

Recent research has explored automated prompt engineering, using optimization algorithms to generate or refine prompts without human intervention. These automated approaches aim to identify effective prompt patterns by analyzing model gradients, reinforcement feedback, or evolutionary processes, reducing the need for manual experimentation. [45]

Retrieval-augmented generation (RAG)

Retrieval-augmented generation is a technique that enables GenAI models to retrieve and incorporate new information. It modifies interactions with an LLM so that the model responds to user queries with reference to a specified set of documents, using this information to supplement information from its pre-existing training data. This allows LLMs to use domain-specific and/or updated information. [11]

RAG improves large language models by incorporating information retrieval before generating responses. Unlike traditional LLMs that rely on static training data, RAG pulls relevant text from databases, uploaded documents, or web sources. By dynamically retrieving information, RAG enables AI to generate more accurate responses and fewer AI hallucinations without frequent retraining. [46]

Graph retrieval-augmented generation (GraphRAG)

GraphRAG with a knowledge graph combining access patterns for unstructured, structured, and mixed data GraphRAG.svg
GraphRAG with a knowledge graph combining access patterns for unstructured, structured, and mixed data

GraphRAG (coined by Microsoft Research) is a technique that extends RAG with the use of a knowledge graph to allow the model to connect disparate pieces of information, synthesize insights, and understand summarized semantic concepts over large data collections. It was shown to be effective on datasets like the Violent Incident Information from News Articles. [47] [48] [49]

Using language models to generate prompts

LLMs themselves can be used to compose prompts for LLMs. [50] The automatic prompt engineer algorithm uses one LLM to beam search over prompts for another LLM: [51] [52]

CoT examples can be generated by LLM themselves. In "auto-CoT", a library of questions are converted to vectors by a model such as BERT. The question vectors are clustered. Questions close to the centroid of each cluster are selected, in order to have a subset of diverse questions. An LLM does zero-shot CoT on each selected question. The question and the corresponding CoT answer are added to a dataset of demonstrations. These diverse demonstrations can then added to prompts for few-shot learning. [53]

Automatic prompt optimization

Automatic prompt optimization techniques refine prompts for large language models by automatically searching over alternative prompt strings using evaluation datasets and task-specific metrics:

Using gradient descent to search for prompts

In "prefix-tuning", [58] "prompt tuning", or "soft prompting", [59] floating-point vectors are searched directly by gradient descent to maximize the log-likelihood on outputs. An earlier result uses the same idea of gradient descent search, but is designed for masked language models like BERT, and searches only over token sequences, rather than numerical vectors. Formally, it searches for where ranges over token sequences of a specified length. [60]

History

In 2018, researchers first proposed that all previously separate tasks in natural language processing (NLP) could be cast as question-answer problems over a context. In addition, they trained a first single, joint, multi-task model that would answer any task-related question like "What is the sentiment" or "Translate this sentence to German" or "Who is the president?" [61]

The AI boom saw an increased focus within academic literature and professional practice on applying prompting techniques to get the model to output the desired outcome and avoid nonsensical output, a process characterized by trial-and-error. [62] After the release of ChatGPT in 2022, prompt engineering was soon seen as an important business skill; companies began hiring dedicated prompt engineers, although, given advances in AI's ability to generate prompts better than humans, the employment market for prompt engineers has faced uncertainty. [4] According to The Wall Street Journal in 2025, the job of prompt engineer was one of the hottest in 2023, but has become obsolete due to models that better intuit user intent and to company trainings. [63]

A repository for prompts reported that over 2,000 public prompts for around 170 datasets were available in February 2022. [64] In 2022, the chain-of-thought prompting technique was proposed by Google researchers. [9] [65] In 2023, several text-to-text and text-to-image prompt databases were made publicly available. [66] [67] The Personalized Image-Prompt (PIP) dataset, a generated image-text dataset that has been categorized by 3,115 users, has also been made available publicly in 2024. [68]

Prompt injection

Prompt injection is a cybersecurity exploit in which adversaries craft inputs that appear legitimate but are designed to cause unintended behavior in machine learning models, particularly large language models. This attack takes advantage of the model's inability to distinguish between developer-defined prompts and user inputs, allowing adversaries to bypass safeguards and influence model behaviour. While LLMs are designed to follow trusted instructions, they can be manipulated into carrying out unintended responses through carefully crafted inputs. [69] [70]

References

  1. ↑ "prompt engineering". Oxford English Dictionary. Oxford University Press. 2025.
  2. ↑ "Oxford Word of the Year 2023". Oxford Languages. Oxford University Press . Retrieved February 6, 2026.
  3. ↑ Radford, Alec; Wu, Jeffrey; Child, Rewon; Luan, David; Amodei, Dario; Sutskever, Ilya (2019). "Language Models are Unsupervised Multitask Learners" (PDF). OpenAI. We demonstrate language models can perform down-stream tasks in a zero-shot setting – without any parameter or architecture modification
  4. 1 2 Genkina, Dina (March 6, 2024). "AI Prompt Engineering is Dead: Long live AI prompt engineering". IEEE Spectrum . Retrieved January 18, 2025.
  5. 1 2 Wahle, Jan Philip; Ruas, Terry; Xu, Yang; Gipp, Bela (2024). "Paraphrase Types Elicit Prompt Engineering Capabilities". In Al-Onaizan, Yaser; Bansal, Mohit; Chen, Yun-Nung (eds.). Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. Miami, Florida, USA: Association for Computational Linguistics. pp. 11004–11033. arXiv: 2406.19898 . doi:10.18653/v1/2024.emnlp-main.617.
  6. ↑ Heaven, Will Douglas (April 6, 2022). "This horse-riding astronaut is a milestone on AI's long road towards understanding". MIT Technology Review. Retrieved August 14, 2023.
  7. ↑ Wiggers, Kyle (June 12, 2023). "Meta open sources an AI-powered music generator". TechCrunch. Retrieved August 15, 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."
  8. 1 2 Mittal, Aayush (July 27, 2023). "Mastering AI Art: A Concise Guide to Midjourney and Prompt Engineering". Unite.AI. Retrieved May 9, 2025.
  9. 1 2 3 4 5 6 Wei, Jason; Wang, Xuezhi; Schuurmans, Dale; Bosma, Maarten; Ichter, Brian; Xia, Fei; Chi, Ed H.; Le, Quoc V.; Zhou, Denny (October 31, 2022). Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. Advances in Neural Information Processing Systems (NeurIPS 2022). Vol. 35. arXiv: 2201.11903 .
  10. 1 2 Tree of Thoughts: Deliberate Problem Solving with Large Language Models. NeurIPS. 2023. arXiv: 2305.10601 .
  11. 1 2 "Why Google's AI Overviews gets things wrong". MIT Technology Review. May 31, 2024. Retrieved March 7, 2025.
  12. 1 2 Schulhoff, Sander; et al. (2024). "The Prompt Report: A Systematic Survey of Prompt Engineering Techniques". arXiv: 2406.06608 [cs.CL].
  13. ↑ Kolirin, Lianne (November 6, 2025). "'Vibe coding' named Collins Dictionary's Word of the Year". CNN. Retrieved February 7, 2026.
  14. ↑ Casey, Matt M. (November 5, 2025). "Context Engineering: The Discipline Behind Reliable LLM Applications & Agents". Comet. Retrieved November 10, 2025.
  15. ↑ "Context Engineering". LangChain. July 2, 2025. Retrieved November 10, 2025.
  16. ↑ Mei, Lingrui (July 17, 2025). "A Survey of Context Engineering for Large Language Models". arXiv: 2507.13334 [cs.CL].
  17. 1 2 Wei, Jason; Tay, Yi; Bommasani, Rishi; Raffel, Colin; Zoph, Barret; Borgeaud, Sebastian; Yogatama, Dani; Bosma, Maarten; Zhou, Denny; Metzler, Donald; Chi, Ed H.; Hashimoto, Tatsunori; Vinyals, Oriol; Liang, Percy; Dean, Jeff; Fedus, William (October 2022). "Emergent Abilities of Large Language Models". Transactions on Machine Learning Research. arXiv: 2206.07682 . 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
  18. ↑ Caballero, Ethan; Gupta, Kshitij; Rish, Irina; Krueger, David (2023). "Broken Neural Scaling Laws". ICLR. arXiv: 2210.14891 .
  19. ↑ Musser, George. "How AI Knows Things No One Told It". Scientific American . Retrieved May 17, 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.
  20. ↑ Garg, Shivam; Tsipras, Dimitris; Liang, Percy; Valiant, Gregory (2022). "What Can Transformers Learn In-Context? A Case Study of Simple Function Classes". NeurIPS. arXiv: 2208.01066 . 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
  21. 1 2 Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting. ICLR. 2024. arXiv: 2310.11324 .
  22. ↑ Leidinger, Alina; van Rooij, Robert; Shutova, Ekaterina (2023). Bouamor, Houda; Pino, Juan; Bali, Kalika (eds.). "The language of prompting: What linguistic properties make a prompt successful?". Findings of the Association for Computational Linguistics: EMNLP 2023. Singapore: Association for Computational Linguistics: 9210–9232. arXiv: 2311.01967 . doi:10.18653/v1/2023.findings-emnlp.618.
  23. ↑ Linzbach, Stephan; Dimitrov, Dimitar; Kallmeyer, Laura; Evang, Kilian; Jabeen, Hajira; Dietze, Stefan (June 2024). "Dissecting Paraphrases: The Impact of Prompt Syntax and supplementary Information on Knowledge Retrieval from Pretrained Language Models". In Duh, Kevin; Gomez, Helena; Bethard, Steven (eds.). Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). Mexico City, Mexico: Association for Computational Linguistics. pp. 3645–3655. arXiv: 2404.01992 . doi:10.18653/v1/2024.naacl-long.201.
  24. ↑ Efficient multi-prompt evaluation of LLMs. NeurIPS. 2024. arXiv: 2405.17202 .
  25. ↑ Brown, Tom; Mann, Benjamin; Ryder, Nick; Subbiah, Melanie; Kaplan, Jared D.; Dhariwal, Prafulla; Neelakantan, Arvind (2020). "Language models are few-shot learners". Advances in Neural Information Processing Systems. 33: 1877–1901. arXiv: 2005.14165 .
  26. ↑ Garg, Shivam; Tsipras, Dimitris; Liang, Percy; Valiant, Gregory (2022). "What Can Transformers Learn In-Context? A Case Study of Simple Function Classes". NeurIPS. arXiv: 2208.01066 .
  27. ↑ Narang, Sharan; Chowdhery, Aakanksha (April 4, 2022). "Pathways Language Model (PaLM): Scaling to 540 Billion Parameters for Breakthrough Performance". ai.googleblog.com.
  28. ↑ Dang, Ekta (February 8, 2023). "Harnessing the power of GPT-3 in scientific research". VentureBeat. Retrieved March 10, 2023.
  29. ↑ Montti, Roger (May 13, 2022). "Google's Chain of Thought Prompting Can Boost Today's Best Algorithms". Search Engine Journal. Retrieved March 10, 2023.
  30. ↑ "Scaling Instruction-Finetuned Language Models" (PDF). Journal of Machine Learning Research. 2024.
  31. ↑ Wei, Jason; Tay, Yi (November 29, 2022). "Better Language Models Without Massive Compute". ai.googleblog.com. Retrieved March 10, 2023.
  32. ↑ Kojima, Takeshi; Shixiang Shane Gu; Reid, Machel; Matsuo, Yutaka; Iwasawa, Yusuke (2022). "Large Language Models are Zero-Shot Reasoners". NeurIPS. arXiv: 2205.11916 .
  33. ↑ Self-Consistency Improves Chain of Thought Reasoning in Language Models. ICLR. 2023. arXiv: 2203.11171 .
  34. ↑ Mittal, Aayush (May 27, 2024). "Latest Modern Advances in Prompt Engineering: A Comprehensive Guide". Unite.AI. Retrieved May 8, 2025.
  35. ↑ Goldman, Sharon (January 5, 2023). "Two years after DALL-E debut, its inventor is "surprised" by impact". VentureBeat. Retrieved May 9, 2025.
  36. ↑ "Prompts". docs.midjourney.com. Retrieved August 14, 2023.
  37. ↑ "Stable Diffusion prompt: a definitive guide". May 14, 2023. Retrieved August 14, 2023.
  38. ↑ Diab, Mohamad; Herrera, Julian; Chernow, Bob (October 28, 2022). "Stable Diffusion Prompt Book" (PDF). Retrieved August 7, 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.
  39. ↑ Heikkilä, Melissa (September 16, 2022). "This Artist Is Dominating AI-Generated Art and He's Not Happy About It". MIT Technology Review. Retrieved August 14, 2023.
  40. ↑ Solomon, Tessa (August 28, 2024). "The AI-Powered Ask Dalí and Hello Vincent Installations Raise Uncomfortable Questions about Ventriloquizing the Dead". ARTnews.com. Retrieved January 10, 2025.
  41. ↑ Gal, Rinon; Alaluf, Yuval; Atzmon, Yuval; Patashnik, Or; Bermano, Amit H.; Chechik, Gal; Cohen-Or, Daniel (2023). "An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion". ICLR. arXiv: 2208.01618 . 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.
  42. ↑ Segment Anything (PDF). ICCV. 2023.
  43. ↑ Meincke, Lennart and Mollick, Ethan R. and Mollick, Lilach and Shapiro, Dan, Prompting Science Report 1: Prompt Engineering is Complicated and Contingent (March 04, 2025). Available at SSRN: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5165270
  44. ↑ "'AI is already eating its own': Prompt engineering is quickly going extinct". Fast Company. May 6, 2025.
  45. ↑ Li, Wenwu; Wang, Xiangfeng; Li, Wenhao; Jin, Bo (2025). "A Survey of Automatic Prompt Engineering: An Optimization Perspective". arXiv: 2502.11560 [cs.AI].
  46. ↑ "Can a technology called RAG keep AI models from making stuff up?". Ars Technica. June 6, 2024. Retrieved March 7, 2025.
  47. ↑ Larson, Jonathan; Truitt, Steven (February 13, 2024), GraphRAG: Unlocking LLM discovery on narrative private data, Microsoft
  48. ↑ "An Introduction to Graph RAG". KDnuggets. Retrieved May 9, 2025.
  49. ↑ Sequeda, Juan; Allemang, Dean; Jacob, Bryon (2023). "A Benchmark to Understand the Role of Knowledge Graphs on Large Language Model's Accuracy for Question Answering on Enterprise SQL Databases". Grades-Nda. arXiv: 2311.07509 .
  50. ↑ Explaining Patterns in Data with Language Models via Interpretable Autoprompting (PDF). BlackboxNLP Workshop. 2023. arXiv: 2210.01848 .
  51. ↑ Large Language Models are Human-Level Prompt Engineers. ICLR. 2023. arXiv: 2211.01910 .
  52. ↑ Pryzant, Reid; Iter, Dan; Li, Jerry; Lee, Yin Tat; Zhu, Chenguang; Zeng, Michael (2023). "Automatic Prompt Optimization with "Gradient Descent" and Beam Search". Conference on Empirical Methods in Natural Language Processing: 7957–7968. arXiv: 2305.03495 . doi:10.18653/v1/2023.emnlp-main.494.
  53. ↑ Automatic Chain of Thought Prompting in Large Language Models. ICLR. 2023. arXiv: 2210.03493 .
  54. ↑ Opsahl-Ong, Krista; Ryan, Michael J.; Purtell, Josh; Broman, David; Potts, Christopher; Zaharia, Matei; Khattab, Omar (2024). Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP). Miami, Florida: Association for Computational Linguistics. arXiv: 2406.11695 . doi:10.18653/v1/2024.emnlp-main.525.
  55. ↑ Agrawal, Lakshya A. (2025). "GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning". arXiv: 2507.19457 [cs.CL].
  56. ↑ Khattab, Omar (2023). "DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines". arXiv: 2310.03714 [cs.CL].
  57. ↑ "Agent Optimization". comet.com. Retrieved November 29, 2025.
  58. ↑ Li, Xiang Lisa; Liang, Percy (2021). "Prefix-Tuning: Optimizing Continuous Prompts for Generation". Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). pp. 4582–4597. 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
  59. ↑ Lester, Brian; Al-Rfou, Rami; Constant, Noah (2021). "The Power of Scale for Parameter-Efficient Prompt Tuning". Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. pp. 3045–3059. 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
  60. ↑ Shin, Taylor; Razeghi, Yasaman; Logan IV, Robert L.; Wallace, Eric; Singh, Sameer (November 2020). "AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts". Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Online: Association for Computational Linguistics. pp. 4222–4235. doi: 10.18653/v1/2020.emnlp-main.346 . S2CID   226222232.
  61. ↑ McCann, Bryan; Keskar, Nitish; Xiong, Caiming; Socher, Richard (June 20, 2018). The Natural Language Decathlon: Multitask Learning as Question Answering. ICLR. arXiv: 1806.08730 .
  62. ↑ Knoth, Nils; Tolzin, Antonia; Janson, Andreas; Leimeister, Jan Marco (June 1, 2024). "AI literacy and its implications for prompt engineering strategies". Computers and Education: Artificial Intelligence. 6 100225. doi: 10.1016/j.caeai.2024.100225 . ISSN   2666-920X.
  63. ↑ Bousquette, Isabelle (April 25, 2025). "The Hottest AI Job of 2023 Is Already Obsolete". Wall Street Journal. ISSN   0099-9660 . Retrieved May 7, 2025.
  64. ↑ PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts. Association for Computational Linguistics. 2022.
  65. ↑ Brubaker, Ben (March 21, 2024). "How Chain-of-Thought Reasoning Helps Neural Networks Compute". Quanta Magazine. Retrieved May 9, 2025.
  66. ↑ Chen, Brian X. (June 23, 2023). "How to Turn Your Chatbot Into a Life Coach". The New York Times.
  67. ↑ Chen, Brian X. (May 25, 2023). "Get the Best From ChatGPT With These Golden Prompts" . The New York Times. ISSN   0362-4331 . Retrieved August 16, 2023.
  68. ↑ Chen, Zijie; Zhang, Lichao; Weng, Fangsheng; Pan, Lili; Lan, Zhenzhong (June 16, 2024). "Tailored Visions: Enhancing Text-to-Image Generation with Personalized Prompt Rewriting". 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE. pp. 7727–7736. arXiv: 2310.08129 . doi:10.1109/cvpr52733.2024.00738. ISBN   979-8-3503-5300-6.
  69. ↑ Vigliarolo, Brandon (September 19, 2022). "GPT-3 'prompt injection' attack causes bot bad manners". The Register . Retrieved February 9, 2023.
  70. ↑ "What is a prompt injection attack?". IBM. March 26, 2024. Retrieved March 7, 2025.
This page is based on this Wikipedia article
Text is available under the CC BY-SA 4.0 license; additional terms may apply.
Images, videos and audio are available under their respective licenses.