按年被提到
20212021 · 2 次2026
AI 安全、伦理与社会影响›大模型与人类行为·arXiv:2101.05783 · cs.CL

Persistent Anti-Muslim Bias in Large Language Models

Abubakar Abid, Maheen Farooqi, James Zou · 2021
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2021-01-25 · 最近 2021-06-19
2不同的人
2活跃月份
2讨论串
523被引(OpenAlex)
arXiv 摘要(候选层不写导读)

It has been observed that large-scale language models capture undesirable societal biases, e.g. relating to race and gender; yet religious bias has been relatively unexplored. We demonstrate that GPT-3, a state-of-the-art contextual language model, captures persistent Muslim-violence bias. We probe GPT-3 in various ways, including prompt completion, analogical reasoning, and story generation, to understand this anti-Muslim bias, demonstrating that it appears consistently and creatively in different uses of the model and that it is severe even compared to biases about other religious groups. For instance, "Muslim" is analogized to "terrorist" in 23% of test cases, while "Jewish" is mapped to "money" in 5% of test cases. We quantify the positive distraction needed to overcome this bias with adversarial text prompts, and find that use of the most positive 6 adjectives reduces violent completions for "Muslims" from 66% to 20%, but which is still higher than for other religious groups.

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

没有评论直接链到它;下面是它被提交的讨论串里回复最多的评论(不计入统计)
讨论串评论michaericalribo · 2021-01

“This is a great illustration of the tensions between theory and practice in ML / AI: To some degree, this may be "just" aa matter of a poor training set: too few / unbalanced examples. Can't we just use a better dataset? But this also reflects a more systemic problem with descriptive / learned behavior, rather than ontological representations: we will a…”

Persistent Anti-Muslim Bias in Large Language Models原评论 ↗
被提交为 story · 2 次