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

arXiv: https://arxiv.org/abs/2501.13977 · HTML: https://mlsanity.com/paper/2501.13977/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment, refusal and guardrails, one of 12 directions in LLM safety and security.
- Builds on 11 of its 51 references that are in the map.
- First posted on arXiv 23 Jan 2025.

## 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, 11 of 11)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [Fake News Detection on Social Media: A Data Mining Perspective](https://mlsanity.com/paper/1708.01967/) (2017)
- [Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting](https://mlsanity.com/paper/2306.17563/) (2023)
- [Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs](https://mlsanity.com/paper/2402.03927/) (2024)
- [Coverage-based Example Selection for In-Context Learning](https://mlsanity.com/paper/2305.14907/) (2023)
- [Revisiting Zero-Shot Abstractive Summarization in the Era of Large Language Models from the Perspective of Position Bias](https://mlsanity.com/paper/2401.01989/) (2024)
- [Bridging Systems: Open Problems for Countering Destructive Divisiveness across Ranking, Recommenders, and Governance](https://mlsanity.com/paper/2301.09976/) (2023)
- [The closed loop between opinion formation and personalised recommendations](https://mlsanity.com/paper/1809.04644/) (2018)
- [Assessing LLMs for Zero-shot Abstractive Summarization Through the Lens of Relevance Paraphrasing](https://mlsanity.com/paper/2406.03993/) (2024)
- [Harmful YouTube Video Detection: A Taxonomy of Online Harm and MLLMs as Alternative Annotators](https://mlsanity.com/paper/2411.05854/) (2024)

## Built on by (most cited first, 2 of 2)

- [SafeLens: Deliberate and Efficient Video Guardrails with Fast-and-Slow Screening](https://mlsanity.com/paper/2605.17610/) (2026)
- [Beyond a Global Norm: Personalizing Toxicity Sensitivity in Language Models Without Retraining](https://mlsanity.com/paper/2607.23175/) (2026)

## Abstract (arXiv)

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.