# VLM as Policy: Common-Law Content Moderation Framework for Short Video Platform

arXiv: https://arxiv.org/abs/2504.14904 · HTML: https://mlsanity.com/paper/2504.14904/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 58 references that are in the map.
- First posted on arXiv 21 Apr 2025.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [A Holistic Approach to Undesired Content Detection in the Real World](https://mlsanity.com/paper/2208.03274/) (2022)
- [A New Generation of Perspective API: Efficient Multilingual Character-level Transformers](https://mlsanity.com/paper/2202.11176/) (2022)
- [Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese](https://mlsanity.com/paper/2211.01335/) (2022)
- [The Rise of Social Bots](https://mlsanity.com/paper/1407.5225/) (2014)
- [Analyzing the Targets of Hate in Online Social Media](https://mlsanity.com/paper/1603.07709/) (2016)
- [You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content](https://mlsanity.com/paper/2308.05596/) (2023)
- [Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning](https://mlsanity.com/paper/2310.03400/) (2023)
- [EVLM: An Efficient Vision-Language Model for Visual Understanding](https://mlsanity.com/paper/2407.14177/) (2024)
- [A Framework of Severity for Harmful Content Online](https://mlsanity.com/paper/2108.04401/) (2021)
- [Conceptualising Contestability: Perspectives on Contesting Algorithmic Decisions](https://mlsanity.com/paper/2103.01774/) (2021)
- [Multi-modal Misinformation Detection: Approaches, Challenges and Opportunities](https://mlsanity.com/paper/2203.13883/) (2022)
- [Measuring and Characterizing Hate Speech on News Websites](https://mlsanity.com/paper/2005.07926/) (2020)
- [Detecting Rumours with Latency Guarantees using Massive Streaming Data](https://mlsanity.com/paper/2205.06580/) (2022)
- [Harmful YouTube Video Detection: A Taxonomy of Online Harm and MLLMs as Alternative Annotators](https://mlsanity.com/paper/2411.05854/) (2024)
- [Hate Speech Detection on Vietnamese Social Media Text using the Bidirectional-LSTM Model](https://mlsanity.com/paper/1911.03648/) (2019)

## Built on by (most cited first, 21 of 21)

- [Kwai Keye-VL Technical Report](https://mlsanity.com/paper/2507.01949/) (2025)
- [Reasoning-Enhanced Domain-Adaptive Pretraining of Multimodal Large Language Models for Short Video Content Governance](https://mlsanity.com/paper/2509.21486/) (2025)
- [LiViBench: An Omnimodal Benchmark for Interactive Livestream Video Understanding](https://mlsanity.com/paper/2601.15016/) (2026)
- [DOCR-Inspector: Fine-Grained and Automated Evaluation of Document Parsing with VLM](https://mlsanity.com/paper/2512.10619/) (2025)
- [ContextRL: Enhancing MLLM's Knowledge Discovery Efficiency with Context-Augmented RL](https://mlsanity.com/paper/2602.22623/) (2026)
- [Kwai Keye-VL-2.0 Technical Report](https://mlsanity.com/paper/2606.10651/) (2026)
- [Dynamic Content Moderation in Livestreams: Combining Supervised Classification with MLLM-Boosted Similarity Matching](https://mlsanity.com/paper/2512.03553/) (2025)
- [Making MLLMs Blind: Adversarial Smuggling Attacks in MLLM Content Moderation](https://mlsanity.com/paper/2604.06950/) (2026)
- [BLM-Guard: Explainable Multimodal Ad Moderation with Chain-of-Thought and Policy-Aligned Rewards](https://mlsanity.com/paper/2602.18193/) (2026)
- [Evolving Skill-Structured Attack Memory Enhances LLM Jailbreaking](https://mlsanity.com/paper/2605.29237/) (2026)
- [Live or Lie: Action-Aware Capsule Multiple Instance Learning for Risk Assessment in Live Streaming Platforms](https://mlsanity.com/paper/2602.03520/) (2026)
- [Outsmarting the Chameleon: Counterfactual Decoupling for Tactical OOD Shifts in Live Streaming Risk Assessment](https://mlsanity.com/paper/2606.02946/) (2026)
- [MatchLM2Lite: A Scalable MLLM-to-Lite Framework for Reproduced Content Identification](https://mlsanity.com/paper/2606.14786/) (2026)
- [SEEK: Skill-Routed Evaluation with Evolvable Knowledge for Industrial Search](https://mlsanity.com/paper/2609.29803/) (2026)
- [SAGE: Scalable AI Governance & Evaluation](https://mlsanity.com/paper/2602.07840/) (2026)
- [Tool-MCoT: Tool Augmented Multimodal Chain-of-Thought for Content Safety Moderation](https://mlsanity.com/paper/2604.06205/) (2026)
- [SafeLens: Deliberate and Efficient Video Guardrails with Fast-and-Slow Screening](https://mlsanity.com/paper/2605.17610/) (2026)
- [UNIVID: Unified Vision-Language Model for Video Moderation](https://mlsanity.com/paper/2606.05748/) (2026)
- [Whitewashing Hate, Smearing Harmless Content: Annotator-Style Rebuttal Attacks on LLM-Based Moderation](https://mlsanity.com/paper/2608.22230/) (2026)
- [Distributed Implicit Harm: A Compositional Safety Blind Spot in MLLM-Based Video Moderation](https://mlsanity.com/paper/2609.00206/) (2026)
- [SemTree: Judge-Aware Semantic Decision Trees for Inspectable and Repairable Rule Decisions](https://mlsanity.com/paper/2610.13999/) (2026)

## Abstract (arXiv)

Exponentially growing short video platforms (SVPs) face significant challenges in moderating content detrimental to users' mental health, particularly for minors. The dissemination of such content on SVPs can lead to catastrophic societal consequences. Although substantial efforts have been dedicated to moderating such content, existing methods suffer from critical limitations: (1) Manual review is prone to human bias and incurs high operational costs. (2) Automated methods, though efficient, lack nuanced content understanding, resulting in lower accuracy. (3) Industrial moderation regulations struggle to adapt to rapidly evolving trends due to long update cycles. In this paper, we annotate the first SVP content moderation benchmark with authentic user/reviewer feedback to fill the absence of benchmark in this field. Then we evaluate various methods on the benchmark to verify the existence of the aforementioned limitations. We further propose our common-law content moderation framework named KuaiMod to address these challenges. KuaiMod consists of three components: training data construction, offline adaptation, and online deployment & refinement. Leveraging large vision language model (VLM) and Chain-of-Thought (CoT) reasoning, KuaiMod adequately models video toxicity based on sparse user feedback and fosters dynamic moderation policy with rapid update speed and high accuracy. Offline experiments and large-scale online A/B test demonstrates the superiority of KuaiMod: KuaiMod achieves the best moderation performance on our benchmark. The deployment of KuaiMod reduces the user reporting rate by 20% and its application in video recommendation increases both Daily Active User (DAU) and APP Usage Time (AUT) on several Kuaishou scenarios. We have open-sourced our benchmark at https://kuaimod.github.io.