2 papers
cs.CL2026
Cross-Examination Framework: A Task-Agnostic Diagnostic for Information Fidelity in Text-to-Text Generation
Tathagata Raha, Clement Christophe, Nada Saadi +4
Traditional metrics like BLEU and BERTScore fail to capture semantic fidelity in generative text-to-text tasks. We adapt the Cross-Examination Framework (CEF) for a reference-free,…
cs.CL2026
MEDIC: Comprehensive Evaluation of Leading Indicators for LLM Safety and Utility in Clinical Applications
Praveenkumar Kanithi, Clément Christophe, Marco AF Pimentel +8
While Large Language Models (LLMs) achieve superhuman performance on standardized medical licensing exams, these static benchmarks have become saturated and increasingly disconnect…