AffirmativeAI: Towards LGBTQ+ Friendly Audit Frameworks for Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913344700547072 |
|---|---|
| author | Long, Yinru Ma, Zilin Mei, Yiyang Su, Zhaoyuan |
| author_facet | Long, Yinru Ma, Zilin Mei, Yiyang Su, Zhaoyuan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_04652 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AffirmativeAI: Towards LGBTQ+ Friendly Audit Frameworks for Large Language Models Long, Yinru Ma, Zilin Mei, Yiyang Su, Zhaoyuan Human-Computer Interaction 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. |
| title | AffirmativeAI: Towards LGBTQ+ Friendly Audit Frameworks for Large Language Models |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2405.04652 |