Towards Safety and Helpfulness Balanced Responses via Controllable Large Language Models

arXiv:2404.01295v1 Announce Type: new
Abstract: As large language models (LLMs) become easily accessible nowadays, the trade-off between safety and helpfulness can significantly impact user experience. A model that prioritizes safety will cause users to feel less engaged and assisted while prioritizing helpfulness will potentially cause harm. Possible harms include teaching people how to build a bomb, exposing youth to inappropriate content, and hurting users' mental health. In this work, we propose to balance safety and helpfulness in diverse use cases …

abstract arxiv become cs.ai cs.cl experience harm impact language language models large language large language models llms responses safety trade trade-off type via will