IEEE Congress on Evolutionary Computation (CEC) · IEEE WCCI ·
Generate, Verify and Select: Evolutionary Fitness Shaping for Safe Clinical Text Generation
Presented · Conference · Clinical NLP
Checking candidate discharge summaries against clinical constraints reduced medication hallucinations.
Abstract
Automatic generation of clinical discharge summaries, particularly the Brief Hospital Course (BHC) and Discharge Instructions (DI), has gained renewed attention with the release of large-scale benchmarks such as Discharge Me. Although recent large language models achieve strong performance on overlap-based metrics, they frequently hallucinate clinically critical details, including medication names, dosages, numeric quantities, and negations. These errors are weakly penalized by standard evaluation metrics, yet they pose substantial risks in real-world clinical deployment. Motivated by population-based optimization and evolutionary selection principles, we propose Generate–Verify–Select (GVS), an inference-time framework that treats candidate generations as a population evaluated under explicit safety and feasibility constraints. GVS first produces a diverse candidate pool, applies deterministic hard safety gates targeting medication hallucinations, numeric inconsistencies, and negation flips, and filters contradictions using sentence-level natural language inference. Final selection is guided by evolutionary fitness shaping, where a linear fitness function is learned via Differential Evolution to balance multiple, competing quality and safety objectives during output selection. We instantiate GVS for both BHC and DI generation on the Discharge Me benchmark. Without retraining or modifying the underlying generators, GVS improves official automatic evaluation scores (0.323 for BHC and 0.378 for DI) while substantially reducing clinically meaningful hallucinations. GVS cuts medication hallucinations from 20.4–27.8% to 9.2–11.1%, while also halving numeric and negation errors, yielding substantial safety improvements independent of the base model. These results demonstrate that evolutionary selection in output space offers a principled and practical mechanism for enforcing safety and reliability in large language model–based natural language generation, particularly in high-stakes domains.
Findings
- Evaluated on Brief Hospital Course and Discharge Instructions generation in the Discharge Me benchmark.
- Medication hallucinations decrease from 20.4–27.8% to 9.2–11.1% across the reported generators.
- Numeric and negation errors are approximately halved; the underlying generators are not retrained.
Sources and citation
View BibTeX citation
@inproceedings{clinical-generation-2026,
title = {{Generate, Verify and Select: Evolutionary Fitness Shaping for Safe Clinical Text Generation}},
author = {BHVSP Subrahmanyam and Appana Saketh Krishna Rao and Sukriti Tiwari and Neeraj Choudhary},
booktitle = {IEEE Congress on Evolutionary Computation (CEC) · IEEE WCCI},
year = {2026},
url = {https://ieeexplore.ieee.org/document/11727414}
}