In a previous post Ideas to project proposal 1 I discussed a relatively simple way to get GenAI to create a few ideas for a specific project and then create the start of a project proposal.
Now we are going to extend the idea and use Chain of Density Prompt to take the proposal and make it even richer. Chain of Density approach was discussed also in an earlier post Improving your summarising
A proposal is feed in and then an adapted forrm of the Chain of Density is used to refine the detail. The primary idea is that a richer in terms of information is produced.
Prompt
using the loaded file generate increasingly concise entity-dense summarises of the project proposal (now call it Article) . Sections are TITLE; INTRODUCTION ; STATEMENT OF THE PROBLEM ; PURPOSE OF THE STUDY ; ASSUMPTIONS AND HYPOTHESIS; DATA COLLECTION PROCEDURES; DATA ANALYSIS; DATA VALIDATION; ETHICAL ISSUES; REFERENCE LIST.
For each section:
Repeat 5 times, the following steps specified below as Step 1 and Step 2,
Step 1: Identity 1-3 informative Entities (“;” delimited)from the article which are missing from the previous generated summary.
Step 2: Write a new denser summary of identical length which covers every entity and detail from the previous summary plus the Missing Entities.
A Missing Entity is:-
-Relevant: to the section.
-Specific: descriptive yet concise (5 words or fewer).
-Faithful: present in the section.
-Anywhere: located anywhere in the section
Guidelines:
-Make every word count: rewrite the previous summary to improve flow and make space for additional entities.
-Make space with fusion, compression, and removal of uninformative phrases like “the article discusses”.
-The summaries should become highly dense and yet self-contained, e.g. easily understood without the Article.
-Missing entities can appear anywhere in the new section's summary.
-Never drop entities from the previous summary. If space cannot be made, add fewer new entities.
Remember , use exact same number of words for each section summary specified next to Section name (e.g. TITLE (50))
You might need to repeat the process a few times and remember GenAI is not really understanding what it is writing - it still needs the human in the loop.
to read the first post go to: https://llmapplied.blogspot.com/2024/06/genai-productivity-ideas-to-basic.html
Comments
Post a Comment