# Class-RAG: Real-Time Content Moderation with Retrieval Augmented Generation

arXiv: https://arxiv.org/abs/2410.14881 · HTML: https://mlsanity.com/paper/2410.14881/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 22 of its 40 references that are in the map.
- First posted on arXiv 18 Oct 2024.

## Placed in

- Retrieval-augmented generation / [Privacy and security of RAG](https://mlsanity.com/rag/privacy-and-security-of-rag/)

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

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://mlsanity.com/paper/2212.10496/) (2022)
- [Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models](https://mlsanity.com/paper/2211.05105/) (2022)
- [The Faiss library](https://mlsanity.com/paper/2401.08281/) (2024)
- [Retrieval-Augmented Generation for AI-Generated Content: A Survey](https://mlsanity.com/paper/2402.19473/) (2024)
- [Generate rather than Retrieve: Large Language Models are Strong Context Generators](https://mlsanity.com/paper/2209.10063/) (2022)
- [Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack](https://mlsanity.com/paper/2309.15807/) (2023)
- [RAFT: Adapting Language Model to Domain Specific RAG](https://mlsanity.com/paper/2403.10131/) (2024)
- [Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models](https://mlsanity.com/paper/2305.13873/) (2023)
- [Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts](https://mlsanity.com/paper/2309.06135/) (2023)
- [How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval](https://mlsanity.com/paper/2302.07452/) (2023)
- [Latent Guard: a Safety Framework for Text-to-image Generation](https://mlsanity.com/paper/2404.08031/) (2024)
- [UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images](https://mlsanity.com/paper/2405.03486/) (2024)
- [AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policies](https://mlsanity.com/paper/2406.17864/) (2024)
- [Content Moderation by LLM: From Accuracy to Legitimacy](https://mlsanity.com/paper/2409.03219/) (2024)

## Built on by (most cited first, 5 of 5)

- [RAR: Setting Knowledge Tripwires for Retrieval Augmented Rejection](https://mlsanity.com/paper/2505.13581/) (2025)
- [Safeguarding Multimodal Knowledge Copyright in the RAG-as-a-Service Environment](https://mlsanity.com/paper/2506.10030/) (2025)
- [Evaluating LLMs for Demographic-Targeted Social Bias Detection: A Comprehensive Benchmark Study](https://mlsanity.com/paper/2510.04641/) (2025)
- [Adversarial Distilled Retrieval-Augmented Guarding Model for Online Malicious Intent Detection](https://mlsanity.com/paper/2509.14622/) (2025)
- [CHAIRO: Contextual Hierarchical Analogical Induction and Reasoning Optimization for LLMs](https://mlsanity.com/paper/2604.10502/) (2026)

## Abstract (arXiv)

Robust content moderation classifiers are essential for the safety of Generative AI systems. In this task, differences between safe and unsafe inputs are often extremely subtle, making it difficult for classifiers (and indeed, even humans) to properly distinguish violating vs. benign samples without context or explanation. Scaling risk discovery and mitigation through continuous model fine-tuning is also slow, challenging and costly, preventing developers from being able to respond quickly and effectively to emergent harms. We propose a Classification approach employing Retrieval-Augmented Generation (Class-RAG). Class-RAG extends the capability of its base LLM through access to a retrieval library which can be dynamically updated to enable semantic hotfixing for immediate, flexible risk mitigation. Compared to model fine-tuning, Class-RAG demonstrates flexibility and transparency in decision-making, outperforms on classification and is more robust against adversarial attack, as evidenced by empirical studies. Our findings also suggest that Class-RAG performance scales with retrieval library size, indicating that increasing the library size is a viable and low-cost approach to improve content moderation.