improve guides

.gitignore

@@ -0,0 +1,6 @@
+.ipynb_checkpoints/
+__pycache__/
+*.swp
+.env
+.pylintrc
+*.egg-info/

README.md

@@ -37,13 +37,17 @@ The following are a set of guides on prompt engineering developed by us. Guides
 
 - Surveys / Overviews:
 
+  - [Augmented Language Models: a Survey](https://arxiv.org/abs/2302.07842) (Feb 2023)
   - [A Survey for In-context Learning](https://arxiv.org/abs/2301.00234) (Dec 2022)
   - [Towards Reasoning in Large Language Models: A Survey](https://arxiv.org/abs/2212.10403) (Dec 2022)
   - [Emergent Abilities of Large Language Models](https://arxiv.org/abs/2206.07682) (Jun 2022)
   - [A Taxonomy of Prompt Modifiers for Text-To-Image Generation](https://arxiv.org/abs/2204.13988) (Apr 2022)
   - [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://arxiv.org/abs/2107.13586) (Jul 2021)
 - Approaches/Techniques:
 
+  - [À-la-carte Prompt Tuning (APT): Combining Distinct Data Via Composable Prompting](https://arxiv.org/abs/2302.07994) (Feb 2023)
+  - [GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networks](https://arxiv.org/abs/2302.08043) (Feb 2023)
+  - [The Capacity for Moral Self-Correction in Large Language Models](https://arxiv.org/abs/2302.07459) (Feb 2023)
   - [SwitchPrompt: Learning Domain-Specific Gated Soft Prompts for Classification in Low-Resource Domains](https://arxiv.org/abs/2302.06868) (Feb 2023)
   - [Evaluating the Robustness of Discrete Prompts](https://arxiv.org/abs/2302.05619) (Feb 2023)
   - [Compositional Exemplars for In-context Learning](https://arxiv.org/abs/2302.05698) (Feb 2023)
@@ -97,6 +101,8 @@ The following are a set of guides on prompt engineering developed by us. Guides
   - [How Can We Know What Language Models Know?](https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00324/96460/How-Can-We-Know-What-Language-Models-Know) (July 2020)
 - Applications:
 
+  - [LabelPrompt: Effective Prompt-based Learning for Relation Classification](https://arxiv.org/abs/2302.08068) (Feb 2023)
+  - [Prompt Tuning of Deep Neural Networks for Speaker-adaptive Visual Speech Recognition](https://arxiv.org/abs/2302.08102) (Feb 2023)
   - [The Capacity for Moral Self-Correction in Large Language Models](https://arxiv.org/abs/2302.07459) (Feb 2023)
   - [Prompting for Multimodal Hateful Meme Classification](https://arxiv.org/abs/2302.04156) (Feb 2023)
   - [PLACES: Prompting Language Models for Social Conversation Synthesis](https://arxiv.org/abs/2302.03269) (Feb 2023)
@@ -209,6 +215,7 @@ The following are a set of guides on prompt engineering developed by us. Guides
 - [Prompt Engineering Template](https://docs.google.com/spreadsheets/d/1-snKDn38-KypoYCk9XLPg799bHcNFSBAVu2HVvFEAkA/edit#gid=0)
 - [Prompt Engineering Topic by GitHub](https://github.com/topics/prompt-engineering)
 - [Prompt Engineering: From Words to Art](https://www.saxifrage.xyz/post/prompt-engineering)
+- [Prompt Engineering with OpenAI's GPT-3 and other LLMs](https://youtube.com/watch?v=BP9fi_0XTlw&feature=shares)
 - [Prompt injection attacks against GPT-3](https://simonwillison.net/2022/Sep/12/prompt-injection)
 - [Prompt injection to read out the secret OpenAI API key](https://twitter.com/ludwig_stumpp/status/1619701277419794435?s=20&t=GtoMlmYCSt-UmvjqJVbBSA)
 - [Prompting in NLP: Prompt-based zero-shot learning](https://savasy-22028.medium.com/prompting-in-nlp-prompt-based-zero-shot-learning-3f34bfdb2b72)

guides/prompt-miscellaneous.md

@@ -2,7 +2,18 @@
 
 In this section, we discuss other miscellaneous but important topics in prompt engineering.
 
+**Note that this section is under construction.**
+
 
 ---
 ## Multimodal Prompting
-In this section, we will cover some examples of multimodal prompting techniques and applications that leverage multiple modalities as opposed to just text alone.
+In this section, we will cover some examples of multimodal prompting techniques and applications that leverage multiple modalities as opposed to just text alone.
+
+More coming soon!
+
+---
+## GraphPrompts
+
+[Liu et al., 2023](https://arxiv.org/abs/2302.08043) introduces GraphPrompt, a new prompting framework for graphs to improve performance on downstream tasks.
+
+More coming soon!

guides/prompts-advanced-usage.md

@@ -93,7 +93,7 @@ There is no consistency in the format above but that still affect the model from
 
 ## Chain-of-Thought Prompting
 
-Introduced in [Wei et al. (2022)](https://arxiv.org/abs/2201.11903), chain-of-thought (CoT) prompting uses few chain of thought demonstrations are provided as exemplars in prompting to improve the ability of large language models to perform complex reasoning.
+Introduced in [Wei et al. (2022)](https://arxiv.org/abs/2201.11903), chain-of-thought (CoT) prompting enables complex reasoning capabilities through intermediate reasoning steps. You can combine it with few-shot prompting to get better results on more complex tasks that require reasoning before responding.
 
 ```
 The odd numbers in this group add up to an even number: 4, 8, 9, 15, 12, 2, 1.
@@ -138,7 +138,7 @@ Keep in mind that the authors claim that this is an emergent ability that arises
 
 ## Zero-Shot CoT
 
-One recent idea that came out more recently is the idea of [zero-shot CoT](https://arxiv.org/abs/2205.11916) that essentially involves adding "Let's think step by step" to the the original prompt. Let's try a simple problem and see how the model performs:
+One recent idea that came out more recently is the idea of [zero-shot CoT](https://arxiv.org/abs/2205.11916) that essentially involves adding "Let's think step by step" to the original prompt. Let's try a simple problem and see how the model performs:
 
 ```
 I went to the market and bought 10 apples. I gave 2 apples to the neighbor and 2 to the repairman. I then went and bought 5 more apples and ate 1. How many apples did I remain with?
@@ -149,7 +149,7 @@ Output
 11 apples
 ```
 
-The answer is incorrect Now Let's try with the special prompt. 
+The answer is incorrect! Now Let's try with the special prompt. 
 
 ```
 I went to the market and bought 10 apples. I gave 2 apples to the neighbor and 2 to the repairman. I then went and bought 5 more apples and ate 1. How many apples did I remain with?
@@ -171,7 +171,7 @@ It's actually impressive that this simple prompt is effective at this task. This
 
 ## Self-Consistency
 
-Perhaps one of the more advanced techniques out there for prompt engineering is self-consistency. Proposed by [Wang et al. (2022)](https://arxiv.org/pdf/2203.11171.pdf), self-consistency aims "to replace the naive greedy decoding used in chain-of-thought prompting". The idea is to sample multiple, diverse reasoning paths through few-shot CoT, and use the generations to select the most consistent answer. This helps to boost the performance of CoT prompting ont asks involving arithmetic and commonsense reasoning.
+Perhaps one of the more advanced techniques out there for prompt engineering is self-consistency. Proposed by [Wang et al. (2022)](https://arxiv.org/pdf/2203.11171.pdf), self-consistency aims "to replace the naive greedy decoding used in chain-of-thought prompting". The idea is to sample multiple, diverse reasoning paths through few-shot CoT, and use the generations to select the most consistent answer. This helps to boost the performance of CoT prompting on tasks involving arithmetic and commonsense reasoning.
 
 Let's try the following example for arithmetic reasoning:
 
@@ -250,7 +250,7 @@ Computing for the final answer involves a few steps (check out the paper for the
 
 LLMs continue to be improved and one popular technique include the ability to incorporate knowledge or information to help the model make more accurate predictions. 
 
-Using a similar idea, can the model also be used to generate knowledge before making a prediction? That's what attempted in the paper by [Liu et al. 2022](https://arxiv.org/pdf/2110.08387.pdf). In particular, how helpful is this for tasks such as commonsense reasoning?
+Using a similar idea, can the model also be used to generate knowledge before making a prediction? That's what attempted in the paper by [Liu et al. 2022](https://arxiv.org/pdf/2110.08387.pdf) -- generate knowledge to be used as part of the prompt. In particular, how helpful is this for tasks such as commonsense reasoning?
 
 Let's try a simple prompt:
 

guides/prompts-basic-usage.md

@@ -40,7 +40,6 @@ Antibiotics are medications used to treat bacterial infections by either killing
 Without paying too much attention to the accuracy of the output above, which is something we will touch on in a later guide, the model tried to summarize the paragraph in one sentence. You can get clever with the instructions but we will leave that for a later chapter. Feel free to pause here an experiment to see if you get better results.
 
 ---
-
 ## Information Extraction
 While language models are trained to perform natural language generation and related tasks, it's also very capable of performing classification and a range of other natural language processing (NLP) tasks. 
 
@@ -64,6 +63,28 @@ By now it should be obvious that you can ask the model to perform different task
 
 Paragraph source: [ChatGPT: five priorities for research](https://www.nature.com/articles/d41586-023-00288-7) 
 
+---
+## Question Answering
+
+One of the best ways to get the model to respond specific answers is to improve the format of the prompt. As covered before, a prompt could combine instructions, context, input, and output indicator to get improved results. While not components are required, it becomes a good practice as the more specific you are with instruction, the better results you will get. Below is an example of how this would look following a more structured prompt.
+
+```
+Answer the question based on the context below. Keep the answer short and concise. Respond "Unsure about answer" if not sure about the answer.
+
+Context: Teplizumab traces its roots to a New Jersey drug company called Ortho Pharmaceutical. There, scientists generated an early version of the antibody, dubbed OKT3. Originally sourced from mice, the molecule was able to bind to the surface of T cells and limit their cell-killing potential. In 1986, it was approved to help prevent organ rejection after kidney transplants, making it the first therapeutic antibody allowed for human use.
+
+Question: What was OKT3 originally sourced from?
+
+Answer:
+```
+
+Output
+```
+Mice.
+```
+
+Context obtained from [Nature](https://www.nature.com/articles/d41586-023-00400-x).
+
 ---
 
 ## Text Classification