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 models optimized for safety often display exaggerated safety behaviors, such as a tendency to refrain from responding to certain requests as a precautionary measure. As such, a clear trade-off between the helpfulness and safety of these models has been documented in the literature. In this paper, we further investigate the effectiveness of safety measures by evaluating models on already mitigated biases. Using the case of Llama 2 as an example, we illustrate how LLMs' safety responses can still encode harmful assumptions. To do so, we create a set of non-toxic prompts, which we then use to evaluate Llama models. Through our new taxonomy of LLMs responses to users, we observe that the safety/helpfulness trade-offs are more pronounced for certain demographic groups which can lead to quality-of-service harms for marginalized populations.

翻译：大型语言模型（LLMs）的最新进展已推动其在多个领域的广泛应用。然而，这些技术进步也引入了额外的安全风险，并引发了对边缘化群体可能遭受不利影响的担忧。尽管通过监督式安全导向微调、利用基于人类反馈的安全强化学习等缓解措施已逐步建立安全防护机制，但模型的安全性与固有偏见仍存在多重隐忧。此前研究表明，经过安全优化的模型常表现出过度安全行为，例如为规避风险倾向于拒绝响应特定请求。文献已明确记载此类模型在有用性与安全性之间存在显著权衡。本文以Llama 2为案例，通过评估模型对已缓解偏见的处理效能，进一步探究安全措施的有效性。我们构建了一组无毒提示词用于评估Llama系列模型，并通过对用户回应建立新型分类体系，发现安全性与有用性之间的权衡对特定人口群体更为显著，这可能对边缘化群体造成服务质量损害。