AI & Dataset Systems

2 summarised stories about AI & Dataset Systems, each linking back to the original source. Browse all topics →

Friday, 17 July 2026

MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization

arXiv cs.AI 6 hours ago

Researchers released MM-IssueLoc, a benchmark containing 652 issue-PR instances across 23 languages to evaluate how well systems locate bugs in code repositories using both text and visual evidence like screenshots and error dialogs. The strongest evaluated systems achieved 38.96% file-level accuracy at rank 5 and 22.45% function-level accuracy at rank 10, showing current approaches remain far from reliable multimodal localization. The benchmark enables future research to measure whether systems actually use visual information to find issues or rely primarily on text-based approaches.

AI Benchmarking AI Code Generation AI & Computer Vision AI & Dataset Systems

Self-Evolving Human-Centered Framework for Explainable Depression Symptom Annotation

arXiv cs.AI 6 hours ago

Researchers developed an annotation framework that uses large language models with expert review to create explainable depression symptom datasets aligned with DSM-5-TR diagnostic criteria. The framework operates through three stages: candidate evidence selection, criterion-level analysis, and case-level synthesis, with a dual-memory architecture designed to improve annotations through iterative expert feedback without retraining. In pilot testing with expert-reviewed samples, the approach improved annotation consistency and explainability while reducing the need for manual revision.

Aging & Healthcare AI Annotation & Labeling AI & Dataset Systems AI Explainability