Re-ranking Using Large Language Models for Mitigating Exposure to Harmful Content on Social Media Platforms

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Oak, Rajvardhan, Haroon, Muhammad, Jo, Claire, Wojcieszak, Magdalena, Chhabra, Anshuman
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915312282107904
author Oak, Rajvardhan
Haroon, Muhammad
Jo, Claire
Wojcieszak, Magdalena
Chhabra, Anshuman
author_facet Oak, Rajvardhan
Haroon, Muhammad
Jo, Claire
Wojcieszak, Magdalena
Chhabra, Anshuman
contents Social media platforms utilize Machine Learning (ML) and Artificial Intelligence (AI) powered recommendation algorithms to maximize user engagement, which can result in inadvertent exposure to harmful content. Current moderation efforts, reliant on classifiers trained with extensive human-annotated data, struggle with scalability and adapting to new forms of harm. To address these challenges, we propose a novel re-ranking approach using Large Language Models (LLMs) in zero-shot and few-shot settings. Our method dynamically assesses and re-ranks content sequences, effectively mitigating harmful content exposure without requiring extensive labeled data. Alongside traditional ranking metrics, we also introduce two new metrics to evaluate the effectiveness of re-ranking in reducing exposure to harmful content. Through experiments on three datasets, three models and across three configurations, we demonstrate that our LLM-based approach significantly outperforms existing proprietary moderation approaches, offering a scalable and adaptable solution for harm mitigation.
format Preprint
id arxiv_https___arxiv_org_abs_2501_13977
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Re-ranking Using Large Language Models for Mitigating Exposure to Harmful Content on Social Media Platforms
Oak, Rajvardhan
Haroon, Muhammad
Jo, Claire
Wojcieszak, Magdalena
Chhabra, Anshuman
Computation and Language
Artificial Intelligence
Computers and Society
Social and Information Networks
Social media platforms utilize Machine Learning (ML) and Artificial Intelligence (AI) powered recommendation algorithms to maximize user engagement, which can result in inadvertent exposure to harmful content. Current moderation efforts, reliant on classifiers trained with extensive human-annotated data, struggle with scalability and adapting to new forms of harm. To address these challenges, we propose a novel re-ranking approach using Large Language Models (LLMs) in zero-shot and few-shot settings. Our method dynamically assesses and re-ranks content sequences, effectively mitigating harmful content exposure without requiring extensive labeled data. Alongside traditional ranking metrics, we also introduce two new metrics to evaluate the effectiveness of re-ranking in reducing exposure to harmful content. Through experiments on three datasets, three models and across three configurations, we demonstrate that our LLM-based approach significantly outperforms existing proprietary moderation approaches, offering a scalable and adaptable solution for harm mitigation.
title Re-ranking Using Large Language Models for Mitigating Exposure to Harmful Content on Social Media Platforms
topic Computation and Language
Artificial Intelligence
Computers and Society
Social and Information Networks
url https://arxiv.org/abs/2501.13977