Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.01724 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918366207279104 |
|---|---|
| author | Dong, Houde She, Yifei Ye, Kai Su, Liangcai Qian, Chenxiong Hao, Jie |
| author_facet | Dong, Houde She, Yifei Ye, Kai Su, Liangcai Qian, Chenxiong Hao, Jie |
| contents | 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? |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_01724 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GMP: A Benchmark for Content Moderation under Co-occurring Violations and Dynamic Rules Dong, Houde She, Yifei Ye, Kai Su, Liangcai Qian, Chenxiong Hao, Jie Artificial Intelligence 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? |
| title | GMP: A Benchmark for Content Moderation under Co-occurring Violations and Dynamic Rules |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2603.01724 |