Scholarlink

<p>Chang et al. showed that large language models can produce unsafe or biased outputs even when superficially accurate. We highlight that LLMs can hide harmful reasoning if only final responses are red-teamed. Monitoring intermediate inference steps, especially in ethically charged clinical scenarios, can reveal manipulative or unethical thought processes. We propose systematic testing of ethically sensitive prompts and thorough chain-of-thought analysis to ensure safe, trustworthy deployment in healthcare.</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

Reasoning red teaming in healthcare not all paths to a desired outcome are desirable

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年11月12日

查看全文
  • Vera Sorin,
  • Panagiotis Korfiatis,
  • Girish N. Nadkarni,
  • Eyal Klang

摘要

Chang et al. showed that large language models can produce unsafe or biased outputs even when superficially accurate. We highlight that LLMs can hide harmful reasoning if only final responses are red-teamed. Monitoring intermediate inference steps, especially in ethically charged clinical scenarios, can reveal manipulative or unethical thought processes. We propose systematic testing of ethically sensitive prompts and thorough chain-of-thought analysis to ensure safe, trustworthy deployment in healthcare.