# Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis

arXiv: https://arxiv.org/abs/2505.17636 · HTML: https://mlsanity.com/paper/2505.17636/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 40 references that are in the map.
- First posted on arXiv 23 May 2025.

## Builds on (most cited first, 15 of 15)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs](https://mlsanity.com/paper/2406.18495/) (2024)
- [An Overview of Catastrophic AI Risks](https://mlsanity.com/paper/2306.12001/) (2023)
- [Understanding How Dimension Reduction Tools Work: An Empirical Approach to Deciphering t-SNE, UMAP, TriMAP, and PaCMAP for Data Visualization](https://mlsanity.com/paper/2012.04456/) (2020)
- [Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails](https://mlsanity.com/paper/2501.09004/) (2025)
- [SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety](https://mlsanity.com/paper/2404.05399/) (2024)
- [Alignment for Honesty](https://mlsanity.com/paper/2312.07000/) (2023)
- [Examining the robustness of LLM evaluation to the distributional assumptions of benchmarks](https://mlsanity.com/paper/2404.16966/) (2024)
- [Evaluating the Consistency of LLM Evaluators](https://mlsanity.com/paper/2412.00543/) (2024)
- [Metaethical Perspectives on 'Benchmarking' AI Ethics](https://mlsanity.com/paper/2204.05151/) (2022)

## Abstract (arXiv)

Various AI safety datasets have been developed to measure LLMs against evolving interpretations of harm. Our evaluation of five recently published open-source safety benchmarks reveals distinct semantic clusters using UMAP dimensionality reduction and kmeans clustering (silhouette score: 0.470). We identify six primary harm categories with varying benchmark representation. GretelAI, for example, focuses heavily on privacy concerns, while WildGuardMix emphasizes self-harm scenarios. Significant differences in prompt length distribution suggests confounds to data collection and interpretations of harm as well as offer possible context. Our analysis quantifies benchmark orthogonality among AI benchmarks, allowing for transparency in coverage gaps despite topical similarities. Our quantitative framework for analyzing semantic orthogonality across safety benchmarks enables more targeted development of datasets that comprehensively address the evolving landscape of harms in AI use, however that is defined in the future.