AffirmativeAI: Towards LGBTQ+ Friendly Audit Frameworks for Large Language Models

TL;DR

This paper introduces a framework to evaluate and benchmark large language models for their ability to provide affirming, supportive, and accurate responses to LGBTQ+ individuals, aiming to improve mental health support tools.

Contribution

It proposes a novel evaluation framework based on affirmative therapy principles to assess LLMs' affirmativeness towards LGBTQ+ users.

Findings

Developed qualitative and quantitative benchmarks for affirmativeness.

Identified potential harms of general-purpose LLMs in LGBTQ+ mental health support.

Highlighted the importance of culturally sensitive AI responses.

Abstract

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.