Leveraging Large Language Models in Detecting Anti-LGBTQIA+ User-generated Texts
Quoc-Toan Nguyen, Josh Nguyen, Tuan Van Pham, William J. Teahan · 2025
Anti-LGBTQIA+ texts in user-generated content pose significant risks to online safety and inclusivity.This study investigates the capabilities and limitations of five widely adopted Large Language Models (LLMs)-DeepSeek-V3, GPT-4o, GPT-4o-mini, GPT-o1-mini, and Llama3.3-70B-indetecting such harmful content.Our findings reveal that while LLMs demonstrate potential in identifying offensive language, their effectiveness varies across models and metrics, with notable shortcomings in calibration.Furthermore, linguistic analysis exposes deeply embedded patterns of discrimination, reinforcing the urgency for improved detection mechanisms for this marginalised population.In summary, this study demonstrates the significant potential of LLMs for practical application in detecting anti-LGBTQIA+ usergenerated texts and provides valuable insights from text analysis that can inform topic modelling.These findings contribute to developing safer digital platforms and enhancing protection for LGBTQIA+ individuals.△ !Warning: Given the research's objectives, this paper includes profanity, vulgarity, and other harmful language.These may be disturbing for queer or LGBTQIA+ individuals and other readers.