4 papers
Accuracy and Satisfaction in Multi-Turn LLM Dialogues for NFR Assessment
Ali Pourghasemi Fatideh, Wilder Baldwin, Maria Dhakal +2
LLM-based dialogue assistants have become mainstream tools for software developers, yet current evaluation benchmarks focus exclusively on functional correctness. This leaves a cri…
Knowledge Graph Representations for LLM-Based Policy Compliance Reasoning
Wilder Baldwin, Sepideh Ghanavati
The risks posed by AI features are increasing as they are rapidly integrated into software applications. In response, regulations and standards for safe and secure AI have been pro…
Ethics Practices in AI Development: An Empirical Study Across Roles and Regions
Wilder Baldwin, Sepideh Ghanavati, Manuel Woersdoerfer
Recent advances in AI applications have raised growing concerns about the need for ethical guidelines and regulations to mitigate the risks posed by these technologies. In this pap…
Generating Privacy Stories From Software Documentation
Wilder Baldwin, Shashank Chintakuntla, Shreyah Parajuli +3
Research shows that analysts and developers consider privacy as a security concept or as an afterthought, which may lead to non-compliance and violation of users' privacy. Most cur…