3 papers
cs.SE2026
RECTIFY: An Interactive Workbench for Post-Evaluation RAG Diagnosis, Repair, and Verification
Keerthana Murugaraj, Salima Lamsiyah, Martin Theobald
Retrieval-Augmented Generation (RAG) evaluators can identify failures such as weak retrieval, poor grounding, incomplete answers, and unsupported generation, but they rarely help d…
cs.CL2025
Automating Historical Insight Extraction from Large-Scale Newspaper Archives via Neural Topic Modeling
Keerthana Murugaraj, Salima Lamsiyah, Marten During +1
Extracting coherent and human-understandable themes from large collections of unstructured historical newspaper archives presents significant challenges due to topic evolution, Opt…
cs.CL2025
RAGVUE: A Diagnostic View for Explainable and Automated Evaluation of Retrieval-Augmented Generation
Keerthana Murugaraj, Salima Lamsiyah, Martin Theobald
Evaluating Retrieval-Augmented Generation (RAG) systems remains a challenging task: existing metrics often collapse heterogeneous behaviors into single scores and provide little in…