Skip to content

feat: groundedness requirement#773

Open
akihikokuroda wants to merge 13 commits intogenerative-computing:mainfrom
akihikokuroda:citation
Open

feat: groundedness requirement#773
akihikokuroda wants to merge 13 commits intogenerative-computing:mainfrom
akihikokuroda:citation

Conversation

@akihikokuroda
Copy link
Copy Markdown
Member

@akihikokuroda akihikokuroda commented Apr 1, 2026

Misc PR

Type of PR

  • Bug Fix
  • New Feature
  • Documentation
  • Other

Description

Testing

  • Tests added to the respective file if code was changed
  • New code has 100% coverage if code as added
  • Ensure existing tests and github automation passes (a maintainer will kick off the github automation when the rest of the PR is populated)

@akihikokuroda akihikokuroda requested a review from a team as a code owner April 1, 2026 20:07
@github-actions
Copy link
Copy Markdown
Contributor

github-actions bot commented Apr 1, 2026

The PR description has been updated. Please fill out the template for your PR to be reviewed.

@akihikokuroda akihikokuroda changed the title groundedness requirement feat: groundedness requirement Apr 1, 2026
@github-actions github-actions bot added the enhancement New feature or request label Apr 1, 2026
Copy link
Copy Markdown
Contributor

@jakelorocco jakelorocco left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is a very interesting requirement. I think it's a good opportunity to show off Mellea intrinsics and requirement checking. I'm not sure we have many other requirements with as many llm calls.

One broader suggestion than the comments I left below: Could we parallelize the steps? Could we generate citations at the same time we check spans for needing citations? As we generate spans that need to be checked, could we check each in parallel or as they are given? If so, I think we should make this requirement work more asynchronously and have an early exit mode if a span fails the check (even if not all citations have been generated / not all spans have been checked).

Signed-off-by: Akihiko Kuroda <akihikokuroda2020@gmail.com>
Signed-off-by: Akihiko Kuroda <akihikokuroda2020@gmail.com>
Signed-off-by: Akihiko Kuroda <akihikokuroda2020@gmail.com>
Signed-off-by: Akihiko Kuroda <akihikokuroda2020@gmail.com>
Signed-off-by: Akihiko Kuroda <akihikokuroda2020@gmail.com>
Signed-off-by: Akihiko Kuroda <akihikokuroda2020@gmail.com>
Signed-off-by: Akihiko Kuroda <akihikokuroda2020@gmail.com>
Signed-off-by: Akihiko Kuroda <akihikokuroda2020@gmail.com>
Signed-off-by: Akihiko Kuroda <akihikokuroda2020@gmail.com>
Signed-off-by: Akihiko Kuroda <akihikokuroda2020@gmail.com>
@psschwei
Copy link
Copy Markdown
Member

psschwei commented Apr 2, 2026

cc @generative-computing/mellea-intrinsics

Signed-off-by: Akihiko Kuroda <akihikokuroda2020@gmail.com>
@akihikokuroda
Copy link
Copy Markdown
Member Author

@jakelorocco Thanks for review. I addressed all your comments except "Could we parallelize the steps?". I'm working on it.

@akihikokuroda
Copy link
Copy Markdown
Member Author

akihikokuroda commented Apr 2, 2026

@jakelorocco There are 2 ideas improve the requirement.
For this:
OPTIMIZED_PIPELINE_DESIGN.md
I'm checking if citation intrinsic works in this usage.

This one does not parallelize the processing but it make a batch call for the citation support step.
COMBINED_SUPPORT_ASSESSMENT_DESIGN.md

Signed-off-by: Akihiko Kuroda <akihikokuroda2020@gmail.com>
@akihikokuroda
Copy link
Copy Markdown
Member Author

The "parallelize" seems some work/investigation necessary. So I improved "citation support" step to make only one LLM call instead of calling LLM for each span.

Signed-off-by: Akihiko Kuroda <akihikokuroda2020@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

enhancement New feature or request

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants