# CoPE: A Small Language Model for Steerable and Scalable Content Labeling

arXiv: https://arxiv.org/abs/2512.18027 · HTML: https://mlsanity.com/paper/2512.18027/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 38 references that are in the map.
- First posted on arXiv 19 Dec 2025.

## Builds on (most cited first, 18 of 18)

- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs](https://mlsanity.com/paper/2406.18495/) (2024)
- [A Holistic Approach to Undesired Content Detection in the Real World](https://mlsanity.com/paper/2208.03274/) (2022)
- [ShieldGemma: Generative AI Content Moderation Based on Gemma](https://mlsanity.com/paper/2407.21772/) (2024)
- [Progent: Securing AI Agents with Privilege Control](https://mlsanity.com/paper/2504.11703/) (2025)
- [Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations](https://mlsanity.com/paper/2411.10414/) (2024)
- [GuardReasoner: Towards Reasoning-based LLM Safeguards](https://mlsanity.com/paper/2501.18492/) (2025)
- [ETHOS: an Online Hate Speech Detection Dataset](https://mlsanity.com/paper/2006.08328/) (2020)
- [Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning](https://mlsanity.com/paper/2310.03400/) (2023)
- [Is LLM an Overconfident Judge? Unveiling the Capabilities of LLMs in Detecting Offensive Language with Annotation Disagreement](https://mlsanity.com/paper/2502.06207/) (2025)
- [Policy-as-Prompt: Turning AI Governance Rules into Guardrails for AI Agents](https://mlsanity.com/paper/2509.23994/) (2025)
- [STAND-Guard: A Small Task-Adaptive Content Moderation Model](https://mlsanity.com/paper/2411.05214/) (2024)
- [What Large Language Models Do Not Talk About: An Empirical Study of Moderation and Censorship Practices](https://mlsanity.com/paper/2504.03803/) (2025)
- [SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior](https://mlsanity.com/paper/2410.16665/) (2024)
- [The Multilingual Divide and Its Impact on Global AI Safety](https://mlsanity.com/paper/2505.21344/) (2025)
- [Reliable Decision from Multiple Subtasks through Threshold Optimization: Content Moderation in the Wild](https://mlsanity.com/paper/2208.07522/) (2022)
- [Large Language Models for Automatic Detection of Sensitive Topics](https://mlsanity.com/paper/2409.00940/) (2024)
- [Probing Association Biases in LLM Moderation Over-Sensitivity](https://mlsanity.com/paper/2505.23914/) (2025)

## Built on by (most cited first, 4 of 4)

- [Positive Alignment: Artificial Intelligence for Human Flourishing](https://mlsanity.com/paper/2605.10310/) (2026)
- [Evaluating Criterion-Conditioned Behaviour of Large Language Models in Content Moderation](https://mlsanity.com/paper/2609.03814/) (2026)
- [StreamDecisionBench: Evaluating Decisions in Force on Evolving Language Streams](https://mlsanity.com/paper/2609.38612/) (2026)
- [To Jev or Not? Evaluating the Accuracy and Efficiency of Structured Decision Models for Hate-Speech Moderation](https://mlsanity.com/paper/2610.03324/) (2026)

## Abstract (arXiv)

This paper details the methodology behind CoPE, a policy-steerable small language model capable of fast and accurate content labeling. We present a novel training curricula called Contradictory Example Training that enables the model to learn policy interpretation rather than mere policy memorization. We also present a novel method for generating content policies, called Binocular Labeling, which enables rapid construction of unambiguous training datasets. When evaluated across seven different harm areas, CoPE exhibits equal or superior accuracy to frontier models at only 1% of their size. We openly release a 9 billion parameter version of the model that can be run on a single consumer-grade GPU. Models like CoPE represent a paradigm shift for classifier systems. By turning an ML task into a policy writing task, CoPE opens up new design possibilities for the governance of online platforms.