Bevan Koopman

Dr ChatGPT tell me what I want to hear: How different prompts impact health answer correctness

2023 · 68 Zit.

ChatGPT Hallucinates when Attributing Answers

2023 · 44 Zit.

Dr ChatGPT, tell me what I want to hear: How prompt knowledge impacts health answer correctness

2023 · 33 Zit. · arXiv (Cornell University)

Generating synthetic clinical text with local large language models to identify misdiagnosed limb fractures in radiology reports

2024 · 8 Zit. · Artificial Intelligence in Medicine

Automated Reconciliation of Radiology Reports and Discharge Summaries.

2015 · 7 Zit. · PubMed

Zero-shot Generative Large Language Models for Systematic Review Screening Automation

2024 · 4 Zit. · arXiv (Cornell University)

Team IELAB at TREC Clinical Trial Track 2023: Enhancing Clinical Trial Retrieval with Neural Rankers and Large Language Models

2024 · 2 Zit. · arXiv (Cornell University)

Generating Natural Language Queries for More Effective Systematic Review Screening Prioritisation

2023 · 0 Zit. · arXiv (Cornell University)