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…
Programming by Chat: A Large-Scale Behavioral Analysis of 11,579 Real-World AI-Assisted IDE Sessions
Ningzhi Tang, Chaoran Chen, Zihan Fang +6
IDE-integrated AI coding assistants, which operate conversationally within developers' working codebases with access to project context and multi-file editing, are rapidly reshapin…
Are you In or Out (of gallery)? Wisdom from the Same-Identity Crowd
Aman Bhatta, Maria Dhakal, Michael C. King +1
A central problem in one-to-many facial identification is that the person in the probe image may or may not have enrolled image(s) in the gallery; that is, may be In-gallery or Out…
AI-Mediated Code Comment Improvement
Maria Dhakal, Chia-Yi Su, Robert Wallace +5
This paper describes an approach to improve code comments along different quality axes by rewriting those comments with customized Artificial Intelligence (AI)-based tools. We cond…