2 papers
cs.CL2025
Do Automatic Factuality Metrics Measure Factuality? A Critical Evaluation
Sanjana Ramprasad, Byron C. Wallace
Modern LLMs can now produce highly readable abstractive summaries, to the point that traditional automated metrics for evaluating summary quality, such as ROUGE, have saturated. Ho…
cs.CL2025
GenAudit: Fixing Factual Errors in Language Model Outputs with Evidence
Kundan Krishna, Sanjana Ramprasad, Prakhar Gupta +3
LLMs can generate factually incorrect statements even when provided access to reference documents. Such errors can be dangerous in high-stakes applications (e.g., document-grounded…