按年被提到
20242026 · 3 次2026
AI 安全、伦理与社会影响›大模型与人类行为·arXiv:2406.17737 · cs.CL

LLM Targeted Underperformance Disproportionately Impacts Vulnerable Users

Elinor Poole-Dayan, Deb Roy, Jad Kabbara · 2024
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2026-04-16 · 最近 2026-07-15
2不同的人
3活跃月份
3讨论串
10被引(OpenAlex)
arXiv 摘要(候选层不写导读)

While state-of-the-art large language models (LLMs) have shown impressive performance on many tasks, there has been extensive research on undesirable model behavior such as hallucinations and bias. In this work, we investigate how the quality of LLM responses changes in terms of information accuracy, truthfulness, and refusals depending on three user traits: English proficiency, education level, and country of origin. We present extensive experimentation on three state-of-the-art LLMs and two different datasets targeting truthfulness and factuality. Our findings suggest that undesirable behaviors in state-of-the-art LLMs occur disproportionately more for users with lower English proficiency, of lower education status, and originating from outside the US, rendering these models unreliable sources of information towards their most vulnerable users.

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yogthos · 2026-07

“While state-of-the-art large language models (LLMs) have shown impressive performance on many tasks, there has been extensive research on undesirable model behavior such as hallucinations and bias. In this work, we investigate how the quality of LLM responses changes in terms of information accuracy, truthfulness, and refusals depending on three user trai…”

Societal Impacts: Claude's values across models and languages原评论 ↗
被提交为 story · 2 次