# XGUARD: A Graded Benchmark for Evaluating Safety Failures of Large Language Models on Extremist Content

arXiv: https://arxiv.org/abs/2506.00973 · HTML: https://mlsanity.com/paper/2506.00973/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 48 references that are in the map.
- First posted on arXiv 1 Jun 2025.

## Builds on (most cited first, 9 of 9)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [Agent-SafetyBench: Evaluating the Safety of LLM Agents](https://mlsanity.com/paper/2412.14470/) (2024)
- [Measuring the Reliability of Hate Speech Annotations: The Case of the European Refugee Crisis](https://mlsanity.com/paper/1701.08118/) (2017)
- [BingoGuard: LLM Content Moderation Tools with Risk Levels](https://mlsanity.com/paper/2503.06550/) (2025)
- [VITAL: A New Dataset for Benchmarking Pluralistic Alignment in Healthcare](https://mlsanity.com/paper/2502.13775/) (2025)
- [Degree based Classification of Harmful Speech using Twitter Data](https://mlsanity.com/paper/1806.04197/) (2018)
- [RealHarm: A Collection of Real-World Language Model Application Failures](https://mlsanity.com/paper/2504.10277/) (2025)
- [GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace](https://mlsanity.com/paper/2505.17078/) (2025)

## Built on by (most cited first, 3 of 3)

- [Evaluating the Robustness of Large Language Model Safety Guardrails Against Adversarial Attacks](https://mlsanity.com/paper/2511.22047/) (2025)
- [Scalable Hierarchical Attention Transformers for Multi-Turn Jailbreak Detection in Long Conversations](https://mlsanity.com/paper/2606.21082/) (2026)
- [Quantifying Behavioral Tails in Black-Box Language Models](https://mlsanity.com/paper/2609.33638/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) can generate content spanning ideological rhetoric to explicit instructions for violence. However, existing safety evaluations often rely on simplistic binary labels (safe and unsafe), overlooking the nuanced spectrum of risk these outputs pose. To address this, we present XGUARD, a benchmark and evaluation framework designed to assess the severity of extremist content generated by LLMs. XGUARD includes 3,840 red teaming prompts sourced from real world data such as social media and news, covering a broad range of ideologically charged scenarios. Our framework categorizes model responses into five danger levels (0 to 4), enabling a more nuanced analysis of both the frequency and severity of failures. We introduce the interpretable Attack Severity Curve (ASC) to visualize vulnerabilities and compare defense mechanisms across threat intensities. Using XGUARD, we evaluate six popular LLMs and two lightweight defense strategies, revealing key insights into current safety gaps and trade-offs between robustness and expressive freedom. Our work underscores the value of graded safety metrics for building trustworthy LLMs.