一项新研究审计了三个AI内容审核系统——OpenAI的moderation endpoint、Meta的Llama Guard和Google的Shield Gemma——以评估它们在治疗应用中的适用性。研究发现，这些旨在避免敏感话题的安全护栏系统可能会阻碍LLM作为治疗师的有效性。研究结果突显了开发用于治疗目的的AI的组织的潜在局限性。 AI
影响 AI内容审核护栏可能会限制LLM在治疗中的有效性，给心理健康领域的AI开发带来挑战。
排序理由 该集群包含一篇详细介绍AI系统审计的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2605.25454v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly being used for emotional support. They are also being developed for formal therapy purposes. However, LLMs like ChaptGPT or Llama are often developed with content moderation guardrails…
Large language models (LLMs) are increasingly being used for emotional support. They are also being developed for formal therapy purposes. However, LLMs like ChaptGPT or Llama are often developed with content moderation guardrails that prevent them from discussing sensitive subje…