From Representational Harms to Quality-of-Service Harms: A Case Study on Llama 2 Safety Safeguards

arXiv:2403.13213v1 Announce Type: new
Abstract: Recent progress in large language models (LLMs) has led to their widespread adoption in various domains. However, these advancements have also introduced additional safety risks and raised concerns regarding their detrimental impact on already marginalized populations. Despite growing mitigation efforts to develop safety safeguards, such as supervised safety-oriented fine-tuning and leveraging safe reinforcement learning from human feedback, multiple concerns regarding the safety and ingrained biases in these models remain. Furthermore, previous work has demonstrated that …

abstract adoption arxiv case case study concerns cs.cl cs.cy cs.lg domains however impact language language models large language large language models llama llama 2 llms progress quality risks safeguards safety service study type