From the 1 of 9 linked papers with an AI index.
9 papers
Pattern over Pixels: Measuring Pattern Completion Bias in Multimodal Code Generation
Khai-Nguyen Nguyen, Oscar Chaparro, Antonio Mastropaolo
Multimodal large language models (MLLMs) are increasingly used to translate webpage screenshots into front-end code, but repeated UI patterns may sway them toward visually incorrec…
Rethinking Issue Resolution for AI/ML Systems
Ahmed Adnan, Mushfiqur Rahman, Antu Saha +1
The paper examines how issue resolution in AI/ML systems differs from traditional software maintenance and proposes tailored frameworks to address challenges like stochastic behavi…
On the Reliability of Code Comprehension Proxies
Erfan Arvan, Nadeeshan De Silva, Oscar Chaparro +1
Prior work on code comprehension uses different comprehension proxies-for example, Likert-scale ratings or answers to input-output questions about program snippets, usually collect…
Verifier Warnings Do Not Improve Comprehensibility Prediction
Nadeeshan De Silva, Martin Kellogg, Oscar Chaparro
Proponents of software verification suggest that code simplicity is linked to the effort to verify code, hypothesizing that formal verifiers produce fewer false positive warnings a…
Recovering Fine-Grained Code Change Rationale from Multiple Software Artifacts
Mehedi Sun, Antu Saha, Nadeeshan De Silva +2
Understanding the reasons behind past code changes is critical for refactoring, code review, and debugging. However, code change rationale is often fragmented, inconsistently docum…
Evaluating Language Model Applications for Identifying Solution-Related Content in Issue Report Discussions
Antu Saha, Mehedi Sun, Oscar Chaparro
During issue resolution, software developers rely on issue reports to discuss solutions for defects, feature requests, and other changes. These discussions contain proposed solutio…