AffirmativeAI：迈向面向大语言模型的 LGBTQ+ 友好审计框架
AffirmativeAI: Towards LGBTQ+ Friendly Audit Frameworks for Large Language Models
AI总结：
本文基于肯定性治疗原则提出 AffirmativeAI 审计框架，结合定性与定量方法评估 LLM 聊天机器人对 LGBTQ+ 心理健康需求的肯定性与潜在危害。
摘要：
LGBTQ+ 群体面临着不成比例的心理健康挑战，包括更高的抑郁、焦虑和自杀意念发生率。研究表明，LGBTQ+ 人群一直在使用基于大语言模型（LLM）的聊天机器人（如 ChatGPT）来满足心理健康需求。尽管这些聊天机器人具备提供即时支持和匿名性的潜力，但其能否给出共情、准确且肯定性的回应仍令人担忧。为应对这些挑战，我们基于肯定性治疗原则提出了一个评估 LLM 肯定性的框架，强调需要以支持和认可 LGBTQ+ 经历的态度、知识与行动。我们建议结合定性与定量分析，希望为“Affirmative AI”建立基准，确保基于 LLM 的聊天机器人能够为 LGBTQ+ 个体提供安全、支持性且有效的心理健康支持。我们对 LLM 的肯定性进行基准测试，并非将其作为 LGBTQ+ 个体的心理健康解决方案，也不声称它能解决其心理健康问题；同时我们强调，在设计技术辅助工具时必须考虑 LGBTQ+ 群体所面临的复杂歧视。鉴于该群体中已有许多人使用 LLM，我们的目标是评估其用于 LGBTQ+ 心理健康支持的表现，以识别在此情境下使用通用 LLM 的潜在危害。
英文摘要：
LGBTQ+ community face disproportionate mental health challenges, including higher rates of depression, anxiety, and suicidal ideation. Research has shown that LGBTQ+ people have been using large language model-based chatbots, such as ChatGPT, for their mental health needs. Despite the potential for immediate support and anonymity these chatbots offer, concerns regarding their capacity to provide empathetic, accurate, and affirming responses remain. In response to these challenges, we propose a framework for evaluating the affirmativeness of LLMs based on principles of affirmative therapy, emphasizing the need for attitudes, knowledge, and actions that support and validate LGBTQ+ experiences. We propose a combination of qualitative and quantitative analyses, hoping to establish benchmarks for "Affirmative AI," ensuring that LLM-based chatbots can provide safe, supportive, and effective mental health support to LGBTQ+ individuals. We benchmark LLM affirmativeness not as a mental health solution for LGBTQ+ individuals or to claim it resolves their mental health issues, as we highlight the need to consider complex discrimination in the LGBTQ+ community when designing technological aids. Our goal is to evaluate LLMs for LGBTQ+ mental health support since many in the community already use them, aiming to identify potential harms of using general-purpose LLMs in this context.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
