Questions about the Rouge metrics

Open
#66 10 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
4/5
Estimated time
3-5 days
Newbie friendliness
25/100
Issue type
Bug
Clarity
Needs clarification
Activity status
Stale
Tech stack
jupyter-notebook

Research direction

No file, test, or entry point is named. Start by locating the Rouge evaluation and comparing the KB generation, standard, and ICL modes against the reported figures; done means identifying and documenting the cause of the metric differences.

Written by the indexing model from the issue text.

Description

1.Why is the kb's rouge metrics particularly low in generation mode, far from icl performance?

2.Why is the rouge metrics higher in standard mode when using KB than in generation mode? there is no essential difference between these two modes of using kb to generate answers.

Image

Image

Dominant language
Jupyter Notebook
Stars
1.5k
Forks
125
Avg merge
22d 8m
Merged PRs (30d)
1

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from microsoft/KBLaM

All issues in microsoft/KBLaM

Similar issues

More Machine Learning issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.