English(EN) Do Large Language Models Show Racial and Sex Bias in Pain Management? A Counterfactual Audit of GPT, Claude, Gemini, Llama, DeepSeek and Qwen

LLM在疼痛管理审计中显示出微小的种族/性别偏见

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-14 05:00

一项对大型语言模型（LLM）的新审计发现，虽然一些模型在疼痛管理场景中表现出偏见，但在纠正后，差异通常可以忽略不计或在统计学上不显著。该研究检查了GPT-4.1 mini、Claude Haiku 4.5、Gemini 2.5 Flash、Llama、DeepSeek和Qwen等模型，测试了它们对涉及不同种族和性别患者的短篇故事的反应。虽然检测到了一些细微差异，特别是在阿片类药物处方决定方面，但研究得出结论，模型的可变性和配置设置比患者身份对结果的影响更大。研究人员建议进行稳健的公平性审计，以考虑模型的不稳定性和多样化的患者代表性。 AI

影响表明当前LLM在疼痛管理等敏感应用中，可能比之前担心的更不容易延续种族和性别偏见。

排序理由学术论文，详细介绍了对多个LLM的偏见审计。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 16 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了对多个LLM的偏见审计。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Richard J. Young, Alice M. Matthews · 2026-11-14 05:00

大型语言模型在疼痛管理中是否表现出种族和性别偏见？对GPT、Claude、Gemini、Llama、DeepSeek和Qwen的反事实审计

arXiv:2611.14935v1 Announce Type: cross Abstract: Racial and ethnic minority patients receive less pain treatment than non-Hispanic White patients, and large language models (LLMs) used as medical AI could reproduce that bias. Prior audits tested a few proprietary models, stated …

本文如何被排名

报道来源 [1]

大型语言模型在疼痛管理中是否表现出种族和性别偏见？对GPT、Claude、Gemini、Llama、DeepSeek和Qwen的反事实审计

相关实体

相关话题