Policy Over Purpose: Auditing LLM Content Moderation of Reclaimed Slur Usage
cs.CL
Submitted: 2026-11-06
Updated: 2026-11-06
Terminology
Sources
- IYKYK (But AI Doesn't): Automated Content Moderation Does Not Capture Communities' Heterogeneous Attitudes Towards Reclaimed Language
- Benchmarking Open-Source Safety Guard Models: A Comprehensive Evaluation
- Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
- A Multi-Perspective Benchmark and Moderation Model for Evaluating Safety and Adversarial Robustness
- Can LLMs Follow Simple Rules?
- Evaluating Large Language Models for Detecting Antisemitism
- Revisiting Prompt Sensitivity in Large Language Models for Text Classification: The Role of Prompt Underspecification
- Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting
- Evaluating the Robustness of Large Language Model Safety Guardrails Against Adversarial Attacks
- ShieldGemma: Generative AI Content Moderation Based on Gemma
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data