Research

Paper

AI LLM March 02, 2026

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

Authors

Houde Dong, Yifei She, Kai Ye, Liangcai Su, Chenxiong Qian, Jie Hao

Abstract

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?

Metadata

arXiv ID: 2603.01724
Provider: ARXIV
Primary Category: cs.AI
Published: 2026-03-02
Fetched: 2026-03-03 04:34

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.01724v1</id>\n    <title>GMP: A Benchmark for Content Moderation under Co-occurring Violations and Dynamic Rules</title>\n    <updated>2026-03-02T10:50:11Z</updated>\n    <link href='https://arxiv.org/abs/2603.01724v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.01724v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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?</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-02T10:50:11Z</published>\n    <arxiv:primary_category term='cs.AI'/>\n    <author>\n      <name>Houde Dong</name>\n    </author>\n    <author>\n      <name>Yifei She</name>\n    </author>\n    <author>\n      <name>Kai Ye</name>\n    </author>\n    <author>\n      <name>Liangcai Su</name>\n    </author>\n    <author>\n      <name>Chenxiong Qian</name>\n    </author>\n    <author>\n      <name>Jie Hao</name>\n    </author>\n  </entry>"
}