Scholarlink

<p>Large language models generate plausible text responses to medical questions, but inaccurate responses pose significant risks in medical decision-making. Grading LLM outputs to determine the best model or answer is time-consuming and impractical in clinical settings; therefore, we introduce EVAL (Expert-of-Experts Verification and Alignment) to streamline this process and enhance LLM safety for upper gastrointestinal bleeding (UGIB). We evaluated OpenAI’s GPT-3.5/4/4o/o1-preview, Anthropic’s Claude-3-Opus, Meta’s LLaMA-2 (7B/13B/70B), and Mistral AI’s Mixtral (7B) across 27 configurations, including zero-shot baseline, retrieval-augmented generation, and supervised fine-tuning. EVAL uses similarity-based ranking and a reward model trained on human-graded responses for rejection sampling. Among the employed similarity metrics, Fine-Tuned ColBERT achieved the highest alignment with human performance across three separate datasets (<i>ρ</i> = 0.81–0.91). The reward model replicated human grading with 87.9% of cases across temperature settings and significantly improved accuracy through rejection sampling by 8.36% overall. EVAL offers scalable potential to assess accuracy for high-stakes medical decision-making.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Expert of Experts Verification and Alignment (EVAL) Framework for Large Language Models Safety in Gastroenterology

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年5月3日

查看全文
  • Mauro Giuffrè,
  • Kisung You,
  • Ziteng Pang,
  • Simone Kresevic,
  • Sunny Chung,
  • Ryan Chen,
  • Youngmin Ko,
  • Colleen Chan,
  • Theo Saarinen,
  • Milos Ajcevic,
  • Lory S. Crocè,
  • Guadalupe Garcia-Tsao,
  • Ian Gralnek,
  • Joseph J. Y. Sung,
  • Alan Barkun,
  • Loren Laine,
  • Jasjeet Sekhon,
  • Bradly Stadie,
  • Dennis L. Shung

摘要

Large language models generate plausible text responses to medical questions, but inaccurate responses pose significant risks in medical decision-making. Grading LLM outputs to determine the best model or answer is time-consuming and impractical in clinical settings; therefore, we introduce EVAL (Expert-of-Experts Verification and Alignment) to streamline this process and enhance LLM safety for upper gastrointestinal bleeding (UGIB). We evaluated OpenAI’s GPT-3.5/4/4o/o1-preview, Anthropic’s Claude-3-Opus, Meta’s LLaMA-2 (7B/13B/70B), and Mistral AI’s Mixtral (7B) across 27 configurations, including zero-shot baseline, retrieval-augmented generation, and supervised fine-tuning. EVAL uses similarity-based ranking and a reward model trained on human-graded responses for rejection sampling. Among the employed similarity metrics, Fine-Tuned ColBERT achieved the highest alignment with human performance across three separate datasets (ρ = 0.81–0.91). The reward model replicated human grading with 87.9% of cases across temperature settings and significantly improved accuracy through rejection sampling by 8.36% overall. EVAL offers scalable potential to assess accuracy for high-stakes medical decision-making.