NLP Wiki

User Tools

Site Tools

Trace: • prompt_engineering • ml_overview
nlp:prompt_engineering

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
nlp:prompt_engineering [2024/06/21 03:41] – [Papers] jmflanignlp:prompt_engineering [2025/10/08 09:16] (current) – [Examples of Prompts] jmflanig
Line 2: Line 2:
  
 ===== Introductions and Overviews ===== ===== Introductions and Overviews =====
 +  * Guides
 +    * [[https://www.datacamp.com/tutorial/a-beginners-guide-to-chatgpt-prompt-engineering|A Beginner's Guide to ChatGPT Prompt Engineering]] Good concise intro (Accessed March 2025)
 +    * **[[https://big-picture.com/media/the_prompt_engineering_cheat_sheet.pdf|The Prompt Engineering Cheat Sheet]]** Great
 +    * [[https://www.promptingguide.ai/|Prompt Engineering Guide]] This one is pretty good
 +    * [[https://cloud.google.com/discover/what-is-prompt-engineering|Google Cloud - Prompt engineering: overview and guide]]
 +  * **Overview Papers**
 +    * [[https://aclanthology.org/2023.findings-emnlp.618.pdf|Leidinger et al 2023 - The language of prompting: What linguistic properties make a prompt successful?]]
 +  * Slides
 +  * Blogs:
 +    * [[https://lilianweng.github.io/posts/2023-03-15-prompt-engineering/|Lil'log Prompt Engineering]]
 +    * Github: [[https://github.com/brexhq/prompt-engineering|BREX's Prompt Engineering Guide]]
 +    * Github: [[https://github.com/dair-ai/Prompt-Engineering-Guide|DAIR AI's Prompt Engineering Guide]]
 +    * Courses
 +      * [[https://learnprompting.org/docs/intro|learnprompting.org]]
   * [[https://github.com/f/awesome-chatgpt-prompts|Awesome ChatGPT Prompts]]   * [[https://github.com/f/awesome-chatgpt-prompts|Awesome ChatGPT Prompts]]
  
Line 11: Line 25:
   * [[https://arxiv.org/pdf/2109.01247.pdf|Webson & Pavlick 2021 - Do Prompt-Based Models Really Understand the Meaning of Their Prompts?]]   * [[https://arxiv.org/pdf/2109.01247.pdf|Webson & Pavlick 2021 - Do Prompt-Based Models Really Understand the Meaning of Their Prompts?]]
   * **[[https://arxiv.org/pdf/2212.10560.pdf|Wang et al 2022 - Self-Instruct: Aligning Language Model with Self Generated Instructions]]**   * **[[https://arxiv.org/pdf/2212.10560.pdf|Wang et al 2022 - Self-Instruct: Aligning Language Model with Self Generated Instructions]]**
 +  * [[https://arxiv.org/pdf/2301.07085|Webson et al 2023 - Are Language Models Worse than Humans at Following Prompts? It's Complicated]]
   * [[https://arxiv.org/pdf/2301.08721.pdf|Cheng et al 2023 - Batch Prompting: Efficient Inference with Large Language Model APIs]] Batch prompting to save money   * [[https://arxiv.org/pdf/2301.08721.pdf|Cheng et al 2023 - Batch Prompting: Efficient Inference with Large Language Model APIs]] Batch prompting to save money
   * [[https://arxiv.org/pdf/2306.01150.pdf|Yin et al 2023 - Did You Read the Instructions? Rethinking the Effectiveness of Task Definitions in Instruction Learning]]   * [[https://arxiv.org/pdf/2306.01150.pdf|Yin et al 2023 - Did You Read the Instructions? Rethinking the Effectiveness of Task Definitions in Instruction Learning]]
Line 17: Line 32:
   * [[https://arxiv.org/abs/2308.05342|Wang & Zhao 2023 - Metacognitive Prompting Improves Understanding   * [[https://arxiv.org/abs/2308.05342|Wang & Zhao 2023 - Metacognitive Prompting Improves Understanding
 in Large Language Models]] in Large Language Models]]
 +  * [[https://arxiv.org/pdf/2503.10084|Zhang et al 2025 - Why Prompt Design Matters and Works: A Complexity Analysis of Prompt Search Space in LLMs]] Shows that naive CoT prompting, like “think step by step,"can severely hinder performance.
 +  * **What makes a good prompt?**
 +    * [[https://aclanthology.org/2023.findings-emnlp.618.pdf|Leidinger et al 2023 - The language of prompting: What linguistic properties make a prompt successful?]]
 +    * [[https://aclanthology.org/2023.findings-emnlp.679.pdf|Gonen et al 2023 - Demystifying Prompts in Language Models via Perplexity Estimation]]
  
 ==== Automatic Prompt Engineering ==== ==== Automatic Prompt Engineering ====
Line 25: Line 44:
   * **[[https://arxiv.org/pdf/2309.03409.pdf|Yang et al 2023 - Large Language Models as Optimizers]]** Figures out a good prompt for the task   * **[[https://arxiv.org/pdf/2309.03409.pdf|Yang et al 2023 - Large Language Models as Optimizers]]** Figures out a good prompt for the task
   * [[https://arxiv.org/pdf/2309.16797.pdf|Ferdando et al 2023 - Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution]]   * [[https://arxiv.org/pdf/2309.16797.pdf|Ferdando et al 2023 - Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution]]
 +  * **Metaprompting**
 +    * Blog posts, etc
 +      * [[https://www.prompthub.us/blog/a-complete-guide-to-meta-prompting|A Complete Guide to Meta Prompting]]
 +      * [[https://www.promptlayer.com/glossary/meta-prompting|Meta-prompting]]
 +      * [[https://community.openai.com/t/meta-prompting-concept-asking-chat-gpt-for-the-best-prompt-for-your-desired-completion-then-to-revise-it-before-using-it/248619|Meta-Prompting Concept: Asking Chat-GPT for the best prompt for your desired completion, then to revise it before using it]]
 +    * [[https://aclanthology.org/2022.coling-1.287v2.pdf|2022 - MetaPrompting: Learning to Learn Better Prompts]]
 +    * [[https://arxiv.org/pdf/2401.12954|2024 - Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding]]
 +
  
 ===== Examples of Prompts ===== ===== Examples of Prompts =====
Line 32: Line 59:
   * [[https://arxiv.org/pdf/2210.02441.pdf|Arora et al 2022 - Ask Me Anything: A Simple Strategy for Prompting Language Models]]   * [[https://arxiv.org/pdf/2210.02441.pdf|Arora et al 2022 - Ask Me Anything: A Simple Strategy for Prompting Language Models]]
   * [[https://github.com/f/awesome-chatgpt-prompts|Awesome ChatGPT Prompts]]   * [[https://github.com/f/awesome-chatgpt-prompts|Awesome ChatGPT Prompts]]
 +  * Prompt to break down sentences into independent facts:
 +{{media:facts-prompt-arxiv-2305.14251.png}}
 +(from [[https://arxiv.org/pdf/2305.14251.pdf|Min 2023]])
 +  * [[https://arxiv.org/pdf/2404.07972|Xie et al 2024 - OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments ]] See the prompts in appendix C
 +
  
 ===== Related Pages ===== ===== Related Pages =====
   * [[Prompting]]   * [[Prompting]]
  
nlp/prompt_engineering.1718941283.txt.gz · Last modified: 2024/06/21 03:41 by jmflanig
Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki