# Are Open-Weight LLMs Ready for Social Media Moderation? A Comparative Study on Bluesky

arXiv: https://arxiv.org/abs/2602.05189 · HTML: https://mlsanity.com/paper/2602.05189/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Safety alignment, refusal and guardrails, one of 12 directions in LLM safety and security.
- Builds on 12 of its 32 references that are in the map.
- First posted on arXiv 5 Feb 2026.

## Placed in

- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Builds on (most cited first, 12 of 12)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [A New Generation of Perspective API: Efficient Multilingual Character-level Transformers](https://mlsanity.com/paper/2202.11176/) (2022)
- [NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model](https://mlsanity.com/paper/2508.14444/) (2025)
- [SLM-Mod: Small Language Models Surpass LLMs at Content Moderation](https://mlsanity.com/paper/2410.13155/) (2024)
- [What Should We Engineer in Prompts? Training Humans in Requirement-Driven LLM Use](https://mlsanity.com/paper/2409.08775/) (2024)
- [An Investigation of Large Language Models for Real-World Hate Speech Detection](https://mlsanity.com/paper/2401.03346/) (2024)
- [Moderating Illicit Online Image Promotion for Unsafe User-Generated Content Games Using Large Vision-Language Models](https://mlsanity.com/paper/2403.18957/) (2024)
- [Disturbed YouTube for Kids: Characterizing and Detecting Inappropriate Videos Targeting Young Children](https://mlsanity.com/paper/1901.07046/) (2019)
- [Open LLMs are Necessary for Current Private Adaptations and Outperform their Closed Alternatives](https://mlsanity.com/paper/2411.05818/) (2024)
- [Bluesky and the AT Protocol: Usable Decentralized Social Media](https://mlsanity.com/paper/2402.03239/) (2024)
- [Safeguarding Decentralized Social Media: LLM Agents for Automating Community Rule Compliance](https://mlsanity.com/paper/2409.08963/) (2024)
- [Looking AT the Blue Skies of Bluesky](https://mlsanity.com/paper/2408.12449/) (2024)

## Abstract (arXiv)

As internet access expands, so does exposure to harmful content, increasing the need for effective moderation. Research has demonstrated that large language models (LLMs) can be effectively utilized for social media moderation tasks, including harmful content detection. While proprietary LLMs have been shown to zero-shot outperform traditional machine learning models, the out-of-the-box capability of open-weight LLMs remains an open question. Motivated by recent developments of reasoning LLMs, we evaluate seven state-of-the-art models: four proprietary and three open-weight. Testing with real-world posts on Bluesky, moderation decisions by Bluesky Moderation Service, and annotations by two authors, we find a considerable degree of overlap between the sensitivity (81%--97%) and specificity (91%--100%) of the open-weight LLMs and those (72%--98%, and 93%--99%) of the proprietary ones. Additionally, our analysis reveals that specificity exceeds sensitivity for rudeness detection, but the opposite holds for intolerance and threats. Lastly, we identify inter-rater agreement across human moderators and the LLMs, highlighting considerations for deploying LLMs in both platform-scale and personalized moderation contexts. These findings show open-weight LLMs can support privacy-preserving moderation on consumer-grade hardware and suggest new directions for designing moderation systems that balance community values with individual user preferences.