18 papers
Beyond the Traceback: Using LLMs for Adaptive Explanations of Programming Errors
Alexandru-Radu Moraru, Shreyan Biswas, Ujwal Gadiraju
Programming error messages are critical for software development, yet they remain difficult for novice programmers to interpret. While Large Language Models (LLMs) can rewrite thes…
The Belief Update Gate: Separating Inertia from Learning in Human-AI Interaction
Shreyan Biswas, Alexander Erlei, Ujwal Gadiraju
Repeated human-AI interaction is often analyzed through pooled belief-updating slopes: users observe AI successes and failures, revise reported beliefs in the feedback-consistent d…
RecQuest: Towards Estimating User Domain Knowledge in Conversational Recommender Systems
Ivica Kostric, Ujwal Gadiraju, Krisztian Balog
The ideal conversational recommender system (CRS) acts like a savvy salesperson, adapting its language and suggestions to a user's expertise level. However, most current systems tr…
AI at the Front Lines of Platform Governance: Using LLMs to Support Illegal Content Reporting under the Digital Services Act
Marie-Therese Sekwenz, Shreyan Biswas, Rita Hermann-Gsenger +1
Illegal content reporting mechanisms are a key technical and organizational measure through which online platforms address illegal content under the European Union Digital Services…
"Label from Somewhere": Reflexive Annotating for Situated AI Alignment
Anne Arzberger, Celine Offerman, Ujwal Gadiraju +2
AI alignment relies on annotator judgments, yet annotation pipelines often treat annotators as interchangeable, obscuring how their social position shapes annotation. We introduce…
Keeping an Eye on AI: A Framework for Effective Human Oversight of AI Systems
Susanne Gaube, Markus Langer, Tim Miller +17
The use of Artificial Intelligence (AI) in high-risk, decision-making scenarios presents technical, safety, and normative challenges; problems that may only be ameliorated by human…