gen-ai
/
Prompt-Engineering-Guide
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fg

pull/38/head
Elvis Saravia 2023-02-27 12:38:27 -06:00
parent f435bc2b7b
commit 2d48f079ef
2 changed files with 6 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
README.md
View File

@ -94,6 +94,7 @@ The following are the latest papers (sorted by release date) on prompt engineeri
- [Teaching Algorithmic Reasoning via In-context Learning](https://arxiv.org/abs/2211.09066) (Nov 2022) - [Teaching Algorithmic Reasoning via In-context Learning](https://arxiv.org/abs/2211.09066) (Nov 2022)
- [Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference](https://arxiv.org/abs/2211.11875) (Nov 2022) - [Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference](https://arxiv.org/abs/2211.11875) (Nov 2022)
- [Ask Me Anything: A simple strategy for prompting language models](https://paperswithcode.com/paper/ask-me-anything-a-simple-strategy-for) (Oct 2022) - [Ask Me Anything: A simple strategy for prompting language models](https://paperswithcode.com/paper/ask-me-anything-a-simple-strategy-for) (Oct 2022)
- [Recitation-Augmented Language Models](https://arxiv.org/abs/2210.01296) (Oct 2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://arxiv.org/abs/2210.03629) (Oct 2022) - [ReAct: Synergizing Reasoning and Acting in Language Models](https://arxiv.org/abs/2210.03629) (Oct 2022)
- [Prompting GPT-3 To Be Reliable](https://arxiv.org/abs/2210.09150) (Oct 2022) - [Prompting GPT-3 To Be Reliable](https://arxiv.org/abs/2210.09150) (Oct 2022)
- [Decomposed Prompting: A Modular Approach for Solving Complex Tasks](https://arxiv.org/abs/2210.02406) (Oct 2022) - [Decomposed Prompting: A Modular Approach for Solving Complex Tasks](https://arxiv.org/abs/2210.02406) (Oct 2022)
@ -212,6 +213,7 @@ The following are the latest papers (sorted by release date) on prompt engineeri
- [A beginner-friendly guide to generative language models - LaMBDA guide](https://aitestkitchen.withgoogle.com/how-lamda-works) - [A beginner-friendly guide to generative language models - LaMBDA guide](https://aitestkitchen.withgoogle.com/how-lamda-works)
- [A Complete Introduction to Prompt Engineering for Large Language Models](https://www.mihaileric.com/posts/a-complete-introduction-to-prompt-engineering) - [A Complete Introduction to Prompt Engineering for Large Language Models](https://www.mihaileric.com/posts/a-complete-introduction-to-prompt-engineering)
- [A Generic Framework for ChatGPT Prompt Engineering](https://medium.com/@thorbjoern.heise/a-generic-framework-for-chatgpt-prompt-engineering-7097f6513a0b) - [A Generic Framework for ChatGPT Prompt Engineering](https://medium.com/@thorbjoern.heise/a-generic-framework-for-chatgpt-prompt-engineering-7097f6513a0b)
- [An SEO’s guide to ChatGPT prompts](https://searchengineland.com/chatgpt-prompts-seo-393523)
- [AI Content Generation](https://www.jonstokes.com/p/ai-content-generation-part-1-machine) - [AI Content Generation](https://www.jonstokes.com/p/ai-content-generation-part-1-machine)
- [AI's rise generates new job title: Prompt engineer](https://www.axios.com/2023/02/22/chatgpt-prompt-engineers-ai-job) - [AI's rise generates new job title: Prompt engineer](https://www.axios.com/2023/02/22/chatgpt-prompt-engineers-ai-job)
- [Awesome ChatGPT Prompts](https://github.com/f/awesome-chatgpt-prompts) - [Awesome ChatGPT Prompts](https://github.com/f/awesome-chatgpt-prompts)
@ -273,6 +275,7 @@ The following are the latest papers (sorted by release date) on prompt engineeri
- [Simulators](https://www.lesswrong.com/posts/vJFdjigzmcXMhNTsx/simulators) - [Simulators](https://www.lesswrong.com/posts/vJFdjigzmcXMhNTsx/simulators)
- [Start with an Instruction](https://beta.openai.com/docs/quickstart/start-with-an-instruction) - [Start with an Instruction](https://beta.openai.com/docs/quickstart/start-with-an-instruction)
- [Talking to machines: prompt engineering & injection](https://artifact-research.com/artificial-intelligence/talking-to-machines-prompt-engineering-injection) - [Talking to machines: prompt engineering & injection](https://artifact-research.com/artificial-intelligence/talking-to-machines-prompt-engineering-injection)
- [Tech’s hottest new job: AI whisperer. No coding required](https://www.washingtonpost.com/technology/2023/02/25/prompt-engineers-techs-next-big-job/)
- [The Book - Fed Honeypot](https://fedhoneypot.notion.site/25fdbdb69e9e44c6877d79e18336fe05?v=1d2bf4143680451986fd2836a04afbf4) - [The Book - Fed Honeypot](https://fedhoneypot.notion.site/25fdbdb69e9e44c6877d79e18336fe05?v=1d2bf4143680451986fd2836a04afbf4)
- [The ChatGPT Prompt Book](https://docs.google.com/presentation/d/17b_ocq-GL5lhV_bYSShzUgxL02mtWDoiw9xEroJ5m3Q/edit#slide=id.gc6f83aa91_0_79) - [The ChatGPT Prompt Book](https://docs.google.com/presentation/d/17b_ocq-GL5lhV_bYSShzUgxL02mtWDoiw9xEroJ5m3Q/edit#slide=id.gc6f83aa91_0_79)
- [The Mirror of Language](https://deepfates.com/the-mirror-of-language) - [The Mirror of Language](https://deepfates.com/the-mirror-of-language)

5
guides/prompts-advanced-usage.md
View File

@ -79,9 +79,6 @@ The answer is True.
That didn't work. It seems like basic standard prompting is not enough to get reliable responses for this type of reasoning problem. The example above provides basic information on the task, even with the examples. If you take a closer look at the task, it does involve more reasoning steps. That didn't work. It seems like basic standard prompting is not enough to get reliable responses for this type of reasoning problem. The example above provides basic information on the task, even with the examples. If you take a closer look at the task, it does involve more reasoning steps.
More recently, chain-of-thought (CoT) prompting has been popularized to address more complex arithmetic,
commonsense, and symbolic reasoning tasks. So let's talk about CoT next and see if we can solve the above task.
Following the findings from [Min et al. (2022)](https://arxiv.org/abs/2202.12837), here a few more tips about demonstrations/exemplars when doing few-shot: Following the findings from [Min et al. (2022)](https://arxiv.org/abs/2202.12837), here a few more tips about demonstrations/exemplars when doing few-shot:
- the label space and the distribution of the input text specified by the demonstrations are both key (regardless of whether the labels are correct - the label space and the distribution of the input text specified by the demonstrations are both key (regardless of whether the labels are correct
@ -124,6 +121,8 @@ There is no consistency in the format above but the model still predicted the co
Overall, it seems that providing examples is useful in some places. When zero-shot prompting and few-shot prompting are not sufficient, it might mean that the whatever was learned by the model isn't enough to do well at the task. From here it is recommended to start thinking about fine-tuning your own models. Overall, it seems that providing examples is useful in some places. When zero-shot prompting and few-shot prompting are not sufficient, it might mean that the whatever was learned by the model isn't enough to do well at the task. From here it is recommended to start thinking about fine-tuning your own models.
More recently, chain-of-thought (CoT) prompting has been popularized to address more complex arithmetic, commonsense, and symbolic reasoning tasks. So let's talk about CoT next and see if we can solve the above task.
--- ---
## Chain-of-Thought Prompting ## Chain-of-Thought Prompting