Recitation Use Cases for Permissioned Content

[fredzannarbor]

Description of the feature request:

I have a use case that suggests the solution needs to be elaborated. I am a book publisher. I publish two types of books: 1) ones that I own the copyright to 2) public domain. In both cases I wish to create front matter sections called "Most Important Passages" and "Striking Words."

The prompts are:

n5. Select the five to seven most important passages of two or three paragraphs long from the manuscript as a whole. Use direct quotations and provide accurate page numbers if available. Output begins: ## Most Important Passages. For each passage, concisely explain why it is important. Output begins: _Rationale:_",

Without using the passages from task 5, select the five most beautiful, striking, memorable, or deeply insightful passages from the document. Provide direct quotations. No rationale. Output begins: ## Striking Passages",

These have recently begun triggering recitation refusals. I believe this is the wrong behavior. My request is fully legal since I am asking the model to repeat permissioned content. Essentially, I am asking for a moderately sophisticated Needle In A Haystack search: find five to seven needles given an abstract description. NIAH is fully within design scope.

A reasonable solution would be to allow the developer to add a flag overriding normal recitation behavior. If necessary, we could fill out a one-time form certifying that we will only do this with permissioned content. Even better would be if I could simply instruct the model "this is permissioned content"!

Please do not close the ticket(s) without addressing this issue. Please contact me for more detail or worked examples.

What problem are you trying to solve with this feature?

first prompt: "Hitting the high points" of a book for a reader in a couple of pages (easily skimmable) that retain the exact wording of the original (so important in a world of sloppy paraphrasing). It's hard to overstate the importance of this in a world where many people do not read books at all (by one estimate, < 50% of Americans read > 1 book a year), young people are bombarded with addictive anti-patterns for reading, lengthy books abound, and evidence shows numerous mental health benefits from reading.

second prompt: identifying "striking" or "beautiful" passages helps with a different aspect of the importance of readers and books, and also serves as a valuable demonstration of the unexpected benefits of LLM in book publishing in a world where many avid readers are skeptical or hostile to "AI".

Any other information you'd like to share?

No response

[singhniraj08]

@fredzannarbor, Thank you reporting this issue.
This repository is for issues related to website(https://ai.google.dev/) like documentation bugs or improvements. For issues related to Gemini API, we would suggest you to use "Send Feedback" option in Gemini docs. Ref: Screenshot below. You can also post this issue on Discourse forum.

[fredzannarbor]

OK, done