Add PerspectiveGap and Magic Words - #35
Open
WhymustIhaveaname wants to merge 1 commit into
Open
Conversation
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds PerspectiveGap (benchmark for multi-agent orchestration prompt writing, 110 scenarios / 10 topologies) to Benchmarks and Evaluation, and Jailbreaking LLMs' Safeguard with Universal Magic Words (universal suffix bypassing embedding-based safety guardrails) to Safety, Red-Teaming, and Alignment.
Note
Low Risk
Documentation-only README list updates with no runtime or configuration changes.
Overview
Extends the Key Research Papers and Benchmarks and Evaluation sections with two curated references.
Under Safety, Red-Teaming, and Alignment, it adds the Universal Magic Words paper (embedding-similarity jailbreak suffixes affecting ChatGPT, DeepSeek, and Qwen). Under Benchmarks and Evaluation, it adds PerspectiveGap as a benchmark for multi-agent orchestration prompt writing (110 scenarios, 10 topologies).
Reviewed by Cursor Bugbot for commit de629e6. Bugbot is set up for automated code reviews on this repo. Configure here.