按年被提到
20222022 · 2 次2026
大模型与语言模型›大模型评测与真实性·arXiv:2207.08143 · cs.CL

Can large language models reason about medical questions?

Valentin Liévin, Christoffer Egeberg Hother, Andreas Geert Motzfeldt, Ole Winther · 2022
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 3 人首次 2022-12-23 · 最近 2023-02-06
3不同的人
2活跃月份
3讨论串
391被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Although large language models (LLMs) often produce impressive outputs, it remains unclear how they perform in real-world scenarios requiring strong reasoning skills and expert domain knowledge. We set out to investigate whether close- and open-source models (GPT-3.5, LLama-2, etc.) can be applied to answer and reason about difficult real-world-based questions. We focus on three popular medical benchmarks (MedQA-USMLE, MedMCQA, and PubMedQA) and multiple prompting scenarios: Chain-of-Thought (CoT, think step-by-step), few-shot and retrieval augmentation. Based on an expert annotation of the generated CoTs, we found that InstructGPT can often read, reason and recall expert knowledge. Last, by leveraging advances in prompt engineering (few-shot and ensemble methods), we demonstrated that GPT-3.5 not only yields calibrated predictive distributions, but also reaches the passing score on three datasets: MedQA-USMLE 60.2%, MedMCQA 62.7% and PubMedQA 78.2%. Open-source models are closing the gap: Llama-2 70B also passed the MedQA-USMLE with 62.5% accuracy.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论ivalm · 2023-02

“With sampling, these models can be relatively well-calibrated [0] but I agree that for a single output, it's a crapshoot. [0] https://arxiv.org/abs/2207.08143”

The fraudulent claims made by IBM about Watson and AI原评论 ↗
被提交为 story · 2 次