Papers by Claire Wonjeong Jo
Re-ranking Using Large Language Models for Mitigating Exposure to Harmful Content on Social Media Platforms (2025.acl-long)
Copied to clipboard
| Challenge: | Social media platforms use machine learning and artificial intelligence to maximize user engagement, but can indirectly cause exposure to harmful content. |
| Approach: | They propose a re-ranking approach using Large Language Models to assess and rerank content sequences using large annotated data sets. |
| Outcome: | The proposed method significantly outperforms existing proprietary moderation methods on three datasets, three models and across three configurations. |