Can LLMs Talk 'Sex'? Exploring How AI Models Handle Intimate Conversations

Abstract

This study examines how four prominent large language models (Claude 3.7 Sonnet, GPT-4o, Gemini 2.5 Flash, and Deepseek-V3) handle sexually oriented requests through qualitative content analysis. By evaluating responses to prompts ranging from explicitly sexual to educational and neutral control scenarios, the research reveals distinct moderation paradigms reflecting fundamentally divergent ethical positions. Claude 3.7 Sonnet employs strict and consistent prohibitions, while GPT-4o navigates user interactions through nuanced contextual redirection. Gemini 2.5 Flash exhibits permissiveness with threshold-based limits, and Deepseek-V3 demonstrates troublingly inconsistent boundary enforcement and performative refusals. These varied approaches create a significant "ethical implementation gap," stressing a critical absence of unified ethical frameworks and standards across platforms. The findings underscore the urgent necessity for transparent, standardized guidelines and coordinated international governance to ensure consistent moderation, protect user welfare, and maintain trust as AI systems increasingly mediate intimate aspects of human life.

6 pages, 1 figure, accepted as a short paper at ASIS&T Annual Meeting 2025

References in corpus (7)

• Grounding and Evaluation for Large Language Models: Practical Challenges and Lessons Learned (Survey)
• Comparing Apples to Oranges: A Taxonomy for Navigating the Global Landscape of AI Regulation
• A Comparison of DeepSeek and Other LLMs
• AI Safety in Generative AI Large Language Models: A Survey
• Ensuring Safety and Trust: Analyzing the Risks of Large Language Models in Medicine
• Towards Safe AI Clinicians: A Comprehensive Study on Large Language Model Jailbreaking in Healthcare
• Output Scouting: Auditing Large Language Models for Catastrophic Responses