Towards Safer Social Media Platforms: Scalable and Performant Few-Shot Harmful Content Moderation Using Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bonagiri, Akash, Li, Lucen, Oak, Rajvardhan, Babar, Zeerak, Wojcieszak, Magdalena, Chhabra, Anshuman
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915119439544320
author Bonagiri, Akash
Li, Lucen
Oak, Rajvardhan
Babar, Zeerak
Wojcieszak, Magdalena
Chhabra, Anshuman
author_facet Bonagiri, Akash
Li, Lucen
Oak, Rajvardhan
Babar, Zeerak
Wojcieszak, Magdalena
Chhabra, Anshuman
contents The prevalence of harmful content on social media platforms poses significant risks to users and society, necessitating more effective and scalable content moderation strategies. Current approaches rely on human moderators, supervised classifiers, and large volumes of training data, and often struggle with scalability, subjectivity, and the dynamic nature of harmful content (e.g., violent content, dangerous challenge trends, etc.). To bridge these gaps, we utilize Large Language Models (LLMs) to undertake few-shot dynamic content moderation via in-context learning. Through extensive experiments on multiple LLMs, we demonstrate that our few-shot approaches can outperform existing proprietary baselines (Perspective and OpenAI Moderation) as well as prior state-of-the-art few-shot learning methods, in identifying harm. We also incorporate visual information (video thumbnails) and assess if different multimodal techniques improve model performance. Our results underscore the significant benefits of employing LLM based methods for scalable and dynamic harmful content moderation online.
format Preprint
id arxiv_https___arxiv_org_abs_2501_13976
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Safer Social Media Platforms: Scalable and Performant Few-Shot Harmful Content Moderation Using Large Language Models
Bonagiri, Akash
Li, Lucen
Oak, Rajvardhan
Babar, Zeerak
Wojcieszak, Magdalena
Chhabra, Anshuman
Computation and Language
Artificial Intelligence
Computers and Society
Social and Information Networks
The prevalence of harmful content on social media platforms poses significant risks to users and society, necessitating more effective and scalable content moderation strategies. Current approaches rely on human moderators, supervised classifiers, and large volumes of training data, and often struggle with scalability, subjectivity, and the dynamic nature of harmful content (e.g., violent content, dangerous challenge trends, etc.). To bridge these gaps, we utilize Large Language Models (LLMs) to undertake few-shot dynamic content moderation via in-context learning. Through extensive experiments on multiple LLMs, we demonstrate that our few-shot approaches can outperform existing proprietary baselines (Perspective and OpenAI Moderation) as well as prior state-of-the-art few-shot learning methods, in identifying harm. We also incorporate visual information (video thumbnails) and assess if different multimodal techniques improve model performance. Our results underscore the significant benefits of employing LLM based methods for scalable and dynamic harmful content moderation online.
title Towards Safer Social Media Platforms: Scalable and Performant Few-Shot Harmful Content Moderation Using Large Language Models
topic Computation and Language
Artificial Intelligence
Computers and Society
Social and Information Networks
url https://arxiv.org/abs/2501.13976