Towards Safety and Helpfulness Balanced Responses via Controllable Large Language Models

YL Tuan, X Chen, EM Smith, L Martin, S Batra… - arXiv preprint arXiv …, 2024 - arxiv.org
As large language models (LLMs) become easily accessible nowadays, the trade-off
between safety and helpfulness can significantly impact user experience. A model that …
被引用次数：10 相关文章

Towards Safety and Helpfulness Balanced Responses via Controllable Large Language Models

YL Tuan, X Chen, EM Smith, L Martin, S Batra… - arXiv e …, 2024 - ui.adsabs.harvard.edu
As large language models (LLMs) become easily accessible nowadays, the trade-off
between safety and helpfulness can significantly impact user experience. A model that …