Papers with reinforcement learning-based rewriting approach
LLM-based Rewriting of Inappropriate Argumentation using Reinforcement Learning from Machine Feedback (2024.acl-long)
Copied to clipboard
| Challenge: | Creating trusted and safe online spaces for people with different backgrounds and opinions is a challenge for social media platforms. |
| Approach: | They propose a reinforcement learning-based rewriting approach that balances content preservation and appropriateness based on existing classifiers. |
| Outcome: | The proposed approach significantly outperforms baselines including few-shot learning, prompting, and humans. |