# ICM-Assistant: Instruction-tuning Multimodal Large Language Models for Rule-based Explainable Image Content Moderation

arXiv: https://arxiv.org/abs/2412.18216 · HTML: https://mlsanity.com/paper/2412.18216/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 15 of its 34 references that are in the map.
- First posted on arXiv 24 Dec 2024.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)

## Builds on (most cited first, 15 of 15)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [ShareGPT4V: Improving Large Multi-Modal Models with Better Captions](https://mlsanity.com/paper/2311.12793/) (2023)
- [mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration](https://mlsanity.com/paper/2311.04257/) (2023)
- [GPTScore: Evaluate as You Desire](https://mlsanity.com/paper/2302.04166/) (2023)
- [A Holistic Approach to Undesired Content Detection in the Real World](https://mlsanity.com/paper/2208.03274/) (2022)
- [InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model](https://mlsanity.com/paper/2401.16420/) (2024)
- [Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models](https://mlsanity.com/paper/2311.06783/) (2023)
- [Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning](https://mlsanity.com/paper/2310.03400/) (2023)
- [Rethinking Multimodal Content Moderation from an Asymmetric Angle with Mixed-modality](https://mlsanity.com/paper/2305.10547/) (2023)
- [Reliable Decision from Multiple Subtasks through Threshold Optimization: Content Moderation in the Wild](https://mlsanity.com/paper/2208.07522/) (2022)
- [VideoModerator: A Risk-aware Framework for Multimodal Video Moderation in E-Commerce](https://mlsanity.com/paper/2109.03479/) (2021)

## Built on by (most cited first, 11 of 11)

- [AesBiasBench: Evaluating Bias and Alignment in Multimodal Language Models for Personalized Image Aesthetic Assessment](https://mlsanity.com/paper/2509.11620/) (2025)
- [Better Reasoning with Less Data: Enhancing VLMs Through Unified Modality Scoring](https://mlsanity.com/paper/2506.08429/) (2025)
- [Embedding-based Retrieval in Multimodal Content Moderation](https://mlsanity.com/paper/2507.01066/) (2025)
- [Towards Trustworthy Multimodal Moderation via Policy-Aligned Reasoning and Hierarchical Labeling](https://mlsanity.com/paper/2508.03296/) (2025)
- [Making MLLMs Blind: Adversarial Smuggling Attacks in MLLM Content Moderation](https://mlsanity.com/paper/2604.06950/) (2026)
- [Aether Weaver: Multimodal Affective Narrative Co-Generation with Dynamic Scene Graphs](https://mlsanity.com/paper/2507.21893/) (2025)
- [CompAgent: An Agentic Framework for Visual Compliance Verification](https://mlsanity.com/paper/2511.00171/) (2025)
- [When Harmful Content Gets Camouflaged: Unveiling Perception Failure of LVLMs with CamHarmTI](https://mlsanity.com/paper/2512.03087/) (2025)
- [CHAIRO: Contextual Hierarchical Analogical Induction and Reasoning Optimization for LLMs](https://mlsanity.com/paper/2604.10502/) (2026)
- [Auditing Exposure to Harmful Content on TikTok using Multimodal Language Models: A Cross-National, Age-Stratified Study](https://mlsanity.com/paper/2608.17583/) (2026)
- [When MLLMs miss what humans read: diagnosing and learning to read squint text](https://mlsanity.com/paper/2610.13465/) (2026)

## Abstract (arXiv)

Controversial contents largely inundate the Internet, infringing various cultural norms and child protection standards. Traditional Image Content Moderation (ICM) models fall short in producing precise moderation decisions for diverse standards, while recent multimodal large language models (MLLMs), when adopted to general rule-based ICM, often produce classification and explanation results that are inconsistent with human moderators. Aiming at flexible, explainable, and accurate ICM, we design a novel rule-based dataset generation pipeline, decomposing concise human-defined rules and leveraging well-designed multi-stage prompts to enrich short explicit image annotations. Our ICM-Instruct dataset includes detailed moderation explanation and moderation Q-A pairs. Built upon it, we create our ICM-Assistant model in the framework of rule-based ICM, making it readily applicable in real practice. Our ICM-Assistant model demonstrates exceptional performance and flexibility. Specifically, it significantly outperforms existing approaches on various sources, improving both the moderation classification (36.8% on average) and moderation explanation quality (26.6% on average) consistently over existing MLLMs. Code/Data is available at https://github.com/zhaoyuzhi/ICM-Assistant.