study
6 notes, newest first.
Evaluating the Impact of Explainable AI on Trust in AI-Assisted Code Review
A study investigates the impact of Explainable AI (XAI) on developers' trust in AI-assisted code reviews. The research compared three LLM-based code review systems with varying levels of XAI support. Results show that…
The Shared Discovery Paradox: How a One-Answer Rule Turns Better Information into Worse Search
The study presents a model that examines how organizations pool dispersed information for decision-making in a discovery problem. It finds that while centralized decision-making can improve beliefs, it may also reduce…
Evaluating RE Practices for Explainability: Synthesizing Insights from Daimler Truck into an Explainable RE Framework Proposal
A study investigates the limitations of current Requirements Engineering (RE) practices in supporting explainability requirements, particularly within industrial contexts. The research focuses on Daimler Truck and…
Playful AI in Professional Email: A Field Experiment on Tone and Recipient Engagement
A study found that using a large language model (GPT-5) to write work emails in a playful tone increased emotional positivity in recipients, while using a professional tone decreased it. However, neither condition…
Playful AI in Professional Email: A Field Experiment on Tone and Recipient Engagement
A study found that using a playful tone in work emails generated by GPT-5 increased emotional positivity in responses, while a professional tone decreased it. However, neither condition directly affected open rates…
Uncertainty Quantification for Computer-Use Agents: A Benchmark across Vision-Language Models and GUI Grounding Datasets
Researchers have developed a benchmark called Argus to test the reliability of computer-use agents that convert vision-language model predictions into executable clicks. The study compares 27 methods across four…
