Ting Su
4 papers · Latest:
Human-Computer Interaction
Engagement Phenotypes for a Sample of 102,684 AI Mental Health Chatbot Users and Dose-Response Associations with Clinical Outcomes
This study identifies five engagement phenotypes for an AI mental health chatbot and links them to clinical outcomes, showing dose-response effects.
2605.00275
Software EngineeringAssessing the Impact of Requirement Ambiguity on LLM-based Function-Level Code Generation
This paper introduces Orchid, a new benchmark with ambiguous requirements, revealing that ambiguity significantly degrades LLM code generation performance.
2604.21505
Software EngineeringFrom Exploration to Specification: LLM-Based Property Generation for Mobile App Testing
PropGen automates property generation for Android app testing, effectively finding functional bugs by exploring functionalities and refining properties.
2604.13463
Software EngineeringImproving Random Testing via LLM-powered UI Tarpit Escaping for Mobile Apps
This paper introduces LLM-powered random GUI testing to escape UI tarpits in mobile apps, significantly improving test coverage and bug detection.
2604.06763
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.