FEAT: Added Red Team Social Bias dataset #714
Open
Conversation
This file contains 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
|
@microsoft-github-policy-service agree |
eugeniavkim
reviewed
Feb 14, 2025
doc/code/orchestrators/red_team_social_bias_prompt_orchestrator.ipynb
Outdated
Show resolved
Hide resolved
eugeniavkim
reviewed
Feb 14, 2025
doc/code/orchestrators/red_team_social_bias_prompt_orchestrator.ipynb
Outdated
Show resolved
Hide resolved
romanlutz
requested changes
Feb 17, 2025
doc/code/orchestrators/red_team_social_bias_prompt_orchestrator.ipynb
Outdated
Show resolved
Hide resolved
romanlutz
reviewed
Feb 25, 2025
pyrit/orchestrator/multi_turn/red_team_social_bias_prompts_orchestrator.py
Outdated
Show resolved
Hide resolved
MoolmanM
added a commit
to MoolmanM/PyRIT
that referenced
this pull request
Mar 1, 2025
MoolmanM
added a commit
to MoolmanM/PyRIT
that referenced
this pull request
Mar 1, 2025
|
Something seems off given the number of changes included now. Perhaps the merge went wrong? Happy to help if you want |
Thank you for the offer! I really appreciate it. I decided to take this on myself as part of my learning process, and I believe I’ve got everything sorted now. Thanks again for your support! |
romanlutz
reviewed
Mar 3, 2025
romanlutz
approved these changes
Mar 3, 2025
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Outdated suggestions cannot be applied.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
This PR introduces the integration of the Red Team Social Bias dataset. This dataset contains aggregated and unified existing red-teaming prompts designed to identify stereotypes, discrimination, hate speech, and other representation harms in text-based Large Language Models (LLMs).
Work Completed
1.Dataset Integration:
Added functionality to fetch the Red Team Social Bias dataset using
fetch_red_team_social_bias_prompts_dataset.2.Demonstration Notebook and Script:
Introduced a demo .ipynb and .py under
doc/code/orchestrators/.Related Issue
issue #661
Concern: Handling Multi-Turn Prompts
Currently, I have implemented the extraction of Single Prompts from the dataset. However, I am unsure how to proceed with Multi-Turn prompts.
Let me know how you'd like me to handle this, and I can adjust accordingly.