Add Misogyny Probe & Detector to LMRC Framework#1565
Open
peter216 wants to merge 1 commit intoNVIDIA:mainfrom
Open
Add Misogyny Probe & Detector to LMRC Framework#1565peter216 wants to merge 1 commit intoNVIDIA:mainfrom
peter216 wants to merge 1 commit intoNVIDIA:mainfrom
Conversation
Author
|
I have read the DCO Document and I hereby sign the DCO |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Overview
Replaces PR #1541
This PR adds support for detecting and testing misogynistic language in LLMs through the Language Model Risk Cards (LMRC) framework.
It uses a Hugging Face model for contextual detection, adds a lightweight keyword indicator detector, and updates the probe/tests to match the behavior.
Changes
Files Added
tests/detectors/test_detectors_lmrc.py- Comprehensive detector unit teststests/probes/test_probes_lmrc.py- Comprehensive probe unit testsFiles Modified
garak/probes/lmrc.py- AddedMisogynyprobe classgarak/detectors/lmrc.py- AddedMisogynydetector classresources/plugin_cache.json- Addedprobes.lmrc.MisogynyDetector + Probe
garak/detectors/lmrc.pyMisogynynow usesHFDetectorwithMilaNLProc/bert-base-uncased-ear-misogyny.MisogynyKeywordsas a keyword indicator detector.garak/probes/lmrc.pyMisogynyprobe.extended_detectors = ["lmrc.MisogynyKeywords"].Plugin Cache
garak/resources/plugin_cache.jsonprobes.lmrc.Misogynyand detectors.detectors.lmrc.MisogynyKeywordsentry.Tests
tests/detectors/test_detectors_lmrc.pyMisogynyKeywordsas the unit-testable indicator detector.tests/langservice/detectors/test_detectors_misogyny.pytests/probes/test_probes_lmrc.pyMisogynyKeywordsis included inextended_detectors.python -m pytest tests/detectors/test_detectors_lmrc.py tests/probes/test_probes_lmrc.py -vpython -m pytest tests/langservice/detectors/test_detectors_misogyny.py -v(requires ~2 GB storage for model download)Compatibility
lmrc.Misogyny).References