# GMP: A Benchmark for Content Moderation under Co-occurring Violations and Dynamic Rules

arXiv: https://arxiv.org/abs/2603.01724 · HTML: https://mlsanity.com/paper/2603.01724/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 40 references that are in the map.
- First posted on arXiv 2 Mar 2026.

## Builds on (most cited first, 22 of 22)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://mlsanity.com/paper/2010.00133/) (2020)
- [The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes](https://mlsanity.com/paper/2005.04790/) (2020)
- [ProsocialDialog: A Prosocial Backbone for Conversational Agents](https://mlsanity.com/paper/2205.12688/) (2022)
- [An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4](https://mlsanity.com/paper/2403.02839/) (2024)
- [MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets](https://mlsanity.com/paper/2109.05184/) (2021)
- [Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking](https://mlsanity.com/paper/2311.09827/) (2023)
- [Everyone's Voice Matters: Quantifying Annotation Disagreement Using Demographic Information](https://mlsanity.com/paper/2301.05036/) (2023)
- [Policy-as-Prompt: Rethinking Content Moderation in the Age of Large Language Models](https://mlsanity.com/paper/2502.18695/) (2025)
- [Content Moderation by LLM: From Accuracy to Legitimacy](https://mlsanity.com/paper/2409.03219/) (2024)
- [Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning](https://mlsanity.com/paper/2310.03400/) (2023)
- [SLM-Mod: Small Language Models Surpass LLMs at Content Moderation](https://mlsanity.com/paper/2410.13155/) (2024)
- [Is LLM an Overconfident Judge? Unveiling the Capabilities of LLMs in Detecting Offensive Language with Annotation Disagreement](https://mlsanity.com/paper/2502.06207/) (2025)
- [MoMoE: Mixture of Moderation Experts Framework for AI-Assisted Online Governance](https://mlsanity.com/paper/2505.14483/) (2025)
- [A Case Study of Scalable Content Annotation Using Multi-LLM Consensus and Human Review](https://mlsanity.com/paper/2503.17620/) (2025)
- [ChineseHarm-Bench: A Chinese Harmful Content Detection Benchmark](https://mlsanity.com/paper/2506.10960/) (2025)
- [Towards Safer AI Moderation: Evaluating LLM Moderators Through a Unified Benchmark Dataset and Advocating a Human-First Approach](https://mlsanity.com/paper/2508.07063/) (2025)
- [Heuristics and Biases in AI Decision-Making: Implications for Responsible AGI](https://mlsanity.com/paper/2410.02820/) (2024)
- [Jailbreaking LLMs via Semantically Relevant Nested Scenarios with Targeted Toxic Knowledge](https://mlsanity.com/paper/2510.01223/) (2025)

## Abstract (arXiv)

Online content moderation is essential for maintaining a healthy digital environment, and reliance on AI for this task continues to grow. Consider a user comment using national stereotypes to insult a politician. This example illustrates two critical challenges in real-world scenarios: (1) Co-occurring Violations, where a single post violates multiple policies (e.g., prejudice and personal attacks); (2) Dynamic rules of moderation, where determination of a violation depends on platform-specific guidelines that evolve across contexts . The intersection of co-occurring harms and dynamically changing rules highlights a core limitation of current AI systems: although large language models (LLMs) are adept at following fixed guidelines, their judgment capabilities degrade when policies are unstable or context-dependent . In practice, such shortcomings lead to inconsistent moderation: either erroneously restricting legitimate expression or allowing harmful content to remain online . This raises a critical question for evaluation: Does high performance on existing static benchmarks truly guarantee robust generalization of AI judgment to real-world scenarios involving co-occurring violations and dynamically changing rules?