Preprint
Jul 2026
Faithful by Design: Evaluating and Improving LLM-Generated Clinical Trial Summaries for Multi-Stakeholder Audiences
A benchmark evaluation framework for measuring the faithfulness of LLM-generated clinical trial summaries across three stakeholder audiences is introduced and a knowledge-graph-augmented retrieval system was developed and evaluated, producing statistically significant improvements in NLI-based faithfulness scores.
Robert W. Williams
· 0 citations