3つの要点 ✔️ InstructGPTを使って対話形式で医療情報を自動的に取得する手法を提案 ✔️ 略語の特定、医学実験の群情報抽出や投薬情報抽出などのタスクを実験 ✔️ Zero-shot, few-shotで従来の先行研究を大幅に上回る精度を達成 Large Language Models are Few-Shot Clinical Information Extractors written by Monica Agrawal, Stefan Hegselmann, Hunter Lang, Yoon Kim, David Sontag (Submitted on 25 May 2022 (v1), last revised 30 Nov 2022 (this version, v2)) Comments: Accepted as a long paper to The 2022
![医療文書からInstructGPTを使って重要情報を抽出する](https://cdn-ak-scissors.b.st-hatena.com/image/square/448111a26b1b691a6752be241942ab3a6b670075/height=288;version=1;width=512/https%3A%2F%2Faisholar.s3.ap-northeast-1.amazonaws.com%2Fmedia%2FApril2023%2Fadafgaehsfhgjtgs.png)