update

Author: mrbullwinkle

articles/cognitive-services/openai/concepts/advanced-prompt-engineering.md

@@ -30,7 +30,7 @@ The Completion API supports the older GPT-3 models and has much more flexible in
 
 ::: zone pivot="programming-language-chat-completions"
 
-[!INCLUDE [Prompt Chat Completion](../includes/chat-completion.md)]
+[!INCLUDE [Prompt Chat Completion](../includes/prompt-chat-completion.md)]
 
 ::: zone-end
 

articles/cognitive-services/openai/includes/prompt-chat-completion.md

@@ -103,9 +103,9 @@ One simple way to use an affordance is to stop generation once the affordance ca
 
 | System message |User     | Assistant  |
 |----------------|---------|------------|
-| You are an AI assistant that helps people find information. | You will read a paragraph, extract factual claims, and then use search engine results to fact-check them<br>---<br>PARAGRAPH<br>John Smith is married to Lucy Smith. They have five kids, and he works as a software engineer at Microsoft. What search queries should I do to fact-check this?<br>---<br>FACTUAL CLAIMS<br>- John Smith is married to Lucy Smith<br>- John and Lucy have five kids<br>- John works as a software engineer at Microsoft<br>---<br>Here are various search queries issued to research the claims above:<br>SEARCH QUERIES<br>- John Smith married to Lucy Smith<br>- John Smith number of children<br>- John Smith software engineer Microsoft<br>---<br>Here are snippets of the search results:<br>SNIPPETS:<br>[1] … John Smith’s wedding was on September 25, 2012 …<br>[2] … John Smith was accompanied by his wife Lucy to a ball<br>[3]John was accompanied to the soccer game by his two daughters and three sons<br>[4] … After spending 10 years at Microsoft, Smith founded his own startup, Tailspin Toys<br>5] John M is the town smith, and he married Fiona. They have a daughter named Lucy<br>---<br>Given the snippets, fact check each of the factual claims above:| -	John Smith is married to Lucy Smith: Confirmed. Snippet [1] and [2] both mention John Smith's wife as Lucy.<br>- John and Lucy have five kids: Confirmed. Snippet [3] mentions that John was accompanied by his two daughters and three sons.<br>- John works as a software engineer at Microsoft: Partially confirmed. Snippet [4] mentions that John spent 10 years at Microsoft, but it does not explicitly state that he currently works there. Further research may be needed to confirm his current employment status.|
+| You are an AI assistant that helps people find information. | You will read a paragraph, extract factual claims, and then use search engine results to fact-check them<br>---<br>PARAGRAPH<br>John Smith is married to Lucy Smith. They have five kids, and he works as a software engineer at Microsoft. What search queries should I do to fact-check this?<br>---<br>FACTUAL CLAIMS<br>- John Smith is married to Lucy Smith<br>- John and Lucy have five kids<br>- John works as a software engineer at Microsoft<br>---<br>Here are various search queries issued to research the claims above:<br>SEARCH QUERIES<br>- John Smith married to Lucy Smith<br>- John Smith number of children<br>- John Smith software engineer Microsoft<br>---<br>Here are snippets of the search results:<br>SNIPPETS:<br>[1] … John Smith’s wedding was on September 25, 2012 …<br>[2] … John Smith was accompanied by his wife Lucy to a ball<br>[3]John was accompanied to the soccer game by his two daughters and three sons<br>[4] … After spending 10 years at Microsoft, Smith founded his own startup, Tailspin Toys<br>5] John M is the town smith, and he married Fiona. They have a daughter named Lucy<br>---<br>Given the snippets, fact check each of the factual claims above:| - John Smith is married to Lucy Smith: Confirmed. Snippet [1] and [2] both mention John Smith's wife as Lucy.<br>- John and Lucy have five kids: Confirmed. Snippet [3] mentions that John was accompanied by his two daughters and three sons.<br>- John works as a software engineer at Microsoft: Partially confirmed. Snippet [4] mentions that John spent 10 years at Microsoft, but it does not explicitly state that he currently works there. Further research may be needed to confirm his current employment status.|
 
-## Specifying the outcome structure
+## Specifying the output structure
 
 Using your prompt to specify the structure of the output can have a significant impact on the nature and quality of the results. Sometimes system message inputs as “only write true facts” or “do not fabricate information” might not be adequate mitigations. Instead, asking for the model response to also include citations can help result in a reduction of the prevalence of incorrect responses.
 

articles/cognitive-services/openai/includes/prompt-completion.md

@@ -50,6 +50,33 @@ In the example below, separators (“---” in this case) have been added betwee
 
 |Prompt|Completion|
 |------|----------|
+|You will read a paragraph, and then issue queries to a search engine in order to fact-check it. Also explain the queries.<br>---<br>PARAGRAPH<br>John Smith is married to Lucy Smith. They have five kids, and he works as a software engineer at Microsoft. What search queries should I do to fact-check this?<br>---<br>QUERIES | . "John Smith Microsoft" - To check if John Smith is indeed employed at Microsoft.<br>2. "John Smith Lucy Smith" - To check if John Smith is married to Lucy Smith.<br>3. "John Smith children" - To check if John Smith has five children.|
+
+If you’re not sure what syntax to use, consider using markdown or XML,  since large language models have been trained on a lot of web content in XML or markdown.
+
+## Break the task down
+
+Models often perform better if the task is broken down into smaller steps. For example, in the search query generation prompt referenced earlier, the prompt can be restructured so that the model is first instructed to extract relevant facts, and then instructed to generate search queries that can be used to verify those facts.
+
+|Prompt|Completion|
+|------|----------|
+|You will read a paragraph, and then issue queries to a search engine in order to fact-check it.<br>---<br>PARAGRAPH<br>John Smith is married to Lucy Smith. They have five kids, and he works as a software engineer at Microsoft. What search queries should I do to fact-check this?<br>Now you will extract factual claims, and issue queries to fact-check them. When issuing a query, use the function SEARCH("query")<br><br>FACTUAL CLAIMS | 1. John Smith is married to Lucy Smith <br>2. They have five kids<br>3. He works as a software engineer at Microsoft<br><br>QUERIES<br>SEARCH("John Smith married Lucy Smith")<br>SEARCH("John Smith family size")<br>SEARCH("John Smith Microsoft software engineer") |
+
+Notice the use of clear syntax to differentiate the sections and prime the output. In this simple example, breaking the task down from one to two steps is not very dramatic, but when trying to do this for a larger piece of text with many factual claims, breaking the task down can make a significant difference.
+
+## Use of affordances
+
+Sometimes we can get the model to use an [affordance](https://www.interaction-design.org/literature/topics/affordances) instead of relying on its own parameters for information and answers. Search, for example, can be an affordance to help mitigate against fabricated answers, and to get up-to-date information.
+
+One simple way to use an affordance is to stop generation once the affordance calls are generated by the model, then paste the outcomes back into the prompt. Below is an example of what the follow-up call could be after doing the **SEARCH** calls above. Notice how we pasted the search results into the prompt and replaced the previous **SEARCH** calls.
+
+|Prompt|Completion|
+|------|----------|
+| You will read a paragraph, extract factual claims, and then use search engine results to fact-check them<br>---<br>PARAGRAPH<br>John Smith is married to Lucy Smith. They have five kids, and he works as a software engineer at Microsoft. What search queries should I do to fact-check this?<br>---<br>FACTUAL CLAIMS<br>- John Smith is married to Lucy Smith<br>- John and Lucy have five kids<br>- John works as a software engineer at Microsoft<br>---<br>Here are various search queries issued to research the claims above:<br>SEARCH QUERIES<br>- John Smith married to Lucy Smith<br>- John Smith number of children<br>- John Smith software engineer Microsoft<br>---<br>Here are snippets of the search results:<br>SNIPPETS:<br>[1] … John Smith’s wedding was on September 25, 2012 …<br>[2] … John Smith was accompanied by his wife Lucy to a ball<br>[3]John was accompanied to the soccer game by his two daughters and three sons<br>[4] … After spending 10 years at Microsoft, Smith founded his own startup, Tailspin Toys<br>5] John M is the town smith, and he married Fiona. They have a daughter named Lucy<br>---<br>Given the snippets, fact check each of the factual claims above: | - John Smith is married to Lucy Smith: Confirmed. Snippet [1] and [2] both mention John Smith's wife as Lucy.<br>- John and Lucy have five kids: Confirmed. Snippet [3] mentions that John was accompanied by his two daughters and three sons.<br>- John works as a software engineer at Microsoft: Partially confirmed. Snippet [4] mentions that John spent 10 years at Microsoft, but it does not explicitly state that he currently works there. Further research may be needed to confirm his current employment status. |  
+
+
+
+