Policy-as-Prompt: Rethinking Content Moderation in the Age of Large Language Models
Preprint
Abstract
Content moderation plays a critical role in shaping safe and inclusive online environments, balancing platform standards, user expectations, and regulatory frameworks. Traditionally, this process involves operationalising policies into guidelines, which are then used by downstream human moderators for enforcement, or to further annotate datasets for training machine learning moderation models. However, recent advancements in large language models (LLMs) are transforming this landscape. These models can now interpret policies directly as textual inputs, eliminating the need for extensive data curation. This approach offers unprecedented flexibility, as moderation can be dynamically adjusted through natural language interactions. This paradigm shift raises important questions about how policies are operationalised and the implications for content moderation practices. In this paper, we formalise the emerging policy-as-prompt framework and identify five key challenges across four domains: Technical Implementation (1. translating policy to prompts, 2. sensitivity to prompt structure and formatting), Sociotechnical (3. the risk of technological determinism in policy formation), Organisational (4. evolving roles between policy and machine learning teams), and Governance (5. model governance and accountability). Through analysing these challenges across technical, sociotechnical, organisational, and governance dimensions, we discuss potential mitigation approaches. This research provides actionable insights for practitioners and lays the groundwork for future exploration of scalable and adaptive content moderation systems in digital ecosystems.Keywords
All Related Versions
This publication has 28 references indexed in Scilit:
- Gen-AI for User Safety: A Survey2024
- One Model Many Scores: Using Multiverse Analysis to Prevent Fairness Hacking and Evaluate the Influence of Model Design Decisions2024
- LLM-Mod: Can Large Language Models Assist Content Moderation?2024
- On Algorithmic Content Moderation2023
- Evolution of bioinformatics and its impact on modern bio-science in the twenty-first century: Special attention to pharmacology, plant science and drug discoveryComputational Toxicology, 2022
- Datasheets for datasetsCommunications of the ACM, 2021
- Fairness definitions explained2018
- Algorithmic regulation: A critical interrogationRegulation & Governance, 2017
- Accountability in algorithmic decision makingCommunications of the ACM, 2016
- Annual IndexIEEE Software, 2005