LLMs Stepping Up to Support Survivors of Technology-Facilitated Abuse
research#llm🔬 Research|Analyzed: Feb 23, 2026 05:03•
Published: Feb 23, 2026 05:00
•1 min read
•ArXiv HCIAnalysis
This research explores the exciting potential of Generative AI to provide support for survivors of technology-facilitated abuse (TFA). The study evaluates the capabilities of different Large Language Models (LLMs) in responding to questions related to TFA, paving the way for innovative applications of AI in this critical area. This work promises to improve accessibility to resources.
Key Takeaways
- •The study assesses how well different Large Language Models (LLMs) answer questions related to technology-facilitated abuse.
- •The evaluation involves both expert analysis and feedback from individuals with experience of TFA.
- •The research aims to inform the design of future LLMs for supporting survivors of intimate partner violence.
Reference / Citation
View Original"In this work, we present the first expert-led manual evaluation of four LLMs - two widely used general-purpose non-reasoning models and two domain-specific models designed for IPV contexts - focused on their effectiveness in responding to TFA-related questions."