Tootfinder

"I Cannot Write This Because It Violates Our Content Policy": Understanding Content Moderation Policies and User Experiences in Generative AI Products
Lan Gao, Oscar Chen, Rachel Lee, Nick Feamster, Chenhao Tan, Marshini Chetty
https://arxiv.org/abs/2506.14018

"I Cannot Write This Because It Violates Our Content Policy": Understanding Content Moderation Policies and User Experiences in Generative AI Products
While recent research has focused on developing safeguards for generative AI (GAI) model-level content safety, little is known about how content moderation to prevent malicious content performs for end-users in real-world GAI products. To bridge this gap, we investigated content moderation policies and their enforcement in GAI online tools -- consumer-facing web-based GAI applications. We first analyzed content moderation policies of 14 GAI online tools. While these policies are comprehensive i…

Mitbekommen? Neben X und #Meta auch #Youtube:
YouTube passt seine #Moderation an und lässt künftig mehr Videos online, auch wenn sie teils gegen Richtlinien verstoßen.
Inhalte mit möglichem …

YouTube has loosened its content moderation policies
YouTube has loosened its content moderation policies, and has told reviewers not to remove potentially policy-violating videos if they’re in the public interest, according to a report from The New York Times.

Improving Regulatory Oversight in Online Content Moderation
Benedetta Tessa, Denise Amram, Anna Monreale, Stefano Cresci
https://arxiv.org/abs/2506.04145 h…

Improving Regulatory Oversight in Online Content Moderation
The European Union introduced the Digital Services Act (DSA) to address the risks associated with digital platforms and promote a safer online environment. However, despite the potential of components such as the Transparency Database, Transparency Reports, and Article 40 of the DSA to improve platform transparency, significant challenges remain. These include data inconsistencies and a lack of detailed information, which hinder transparency in content moderation practices. Additionally, the ab…

Large Language Models for Toxic Language Detection in Low-Resource Balkan Languages
Amel Muminovic, Amela Kadric Muminovic
https://arxiv.org/abs/2506.09992

Large Language Models for Toxic Language Detection in Low-Resource Balkan Languages
Online toxic language causes real harm, especially in regions with limited moderation tools. In this study, we evaluate how large language models handle toxic comments in Serbian, Croatian, and Bosnian, languages with limited labeled data. We built and manually labeled a dataset of 4,500 YouTube and TikTok comments drawn from videos across diverse categories, including music, politics, sports, modeling, influencer content, discussions of sexism, and general topics. Four models (GPT-3.5 Turbo, G…

This https://arxiv.org/abs/2409.03219 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCY_…

Content Moderation by LLM: From Accuracy to Legitimacy
One trending application of LLM (large language model) is to use it for content moderation in online platforms. Most current studies on this application have focused on the metric of accuracy -- the extent to which LLMs make correct decisions about content. This article argues that accuracy is insufficient and misleading because it fails to grasp the distinction between easy cases and hard cases, as well as the inevitable trade-offs in achieving higher accuracy. Closer examination reveals that …