Research:Detecting Peacock behavior with LLMs

Tracked in Phabricator:
Task T368274
Duration:  2024-07 – ??

This page documents a planned research project.
Information may be incomplete and change before the project starts.



Hypothesis

edit

If we train an LLM on detecting peacock behavior, then we can learn if it can detect this policy violation with at least >70% precision and >50% recall and ultimately, decide if said LLM is effective enough to power a new Edit Check and/or Suggested Edit.


Timeline

edit

TDA

References

edit