按年被提到
20242024 · 1 次2026
AI 安全、伦理与社会影响›大模型与人类行为·arXiv:2410.18417 · cs.CL

Large Language Models Reflect the Ideology of their Creators

Maarten Buyl, Alexander Rogiers, Sander Noels, Guillaume Bied, Iris Dominguez-Catena, Edith Heiter, Iman Johary, Alexandru-Cristian Mara, Raphaël Romero, Jefrey Lijffijt, Tijl De Bie · 2024
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2024-10-28 · 最近 2026-09-11
2不同的人
2活跃月份
2讨论串
53被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Large language models (LLMs) are trained on vast amounts of data to generate natural language, enabling them to perform tasks like text summarization and question answering. These models have become popular in artificial intelligence (AI) assistants like ChatGPT and already play an influential role in how humans access information. However, the behavior of LLMs varies depending on their design, training, and use. In this paper, we prompt a diverse panel of popular LLMs to describe a large number of prominent personalities with political relevance, in all six official languages of the United Nations. By identifying and analyzing moral assessments reflected in their responses, we find normative differences between LLMs from different geopolitical regions, as well as between the responses of the same LLM when prompted in different languages. Among only models in the United States, we find that popularly hypothesized disparities in political views are reflected in significant normative differences related to progressive values. Among Chinese models, we characterize a division between internationally- and domestically-focused models. Our results show that the ideological stance of an LLM appears to reflect the worldview of its creators. This poses the risk of political instrumentalization and raises concerns around technological and regulatory efforts with the stated aim of making LLMs ideologically 'unbiased'.

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fithisux · 2024-10

“It doesn't take science to understand that. LLMS are a reflection of us. “Mirror, Mirror on the wall, who's the fairest of them all?””

Large Language Models Reflect the Ideology of Their Creators原评论 ↗
讨论串评论dtagames · 2024-10

“This article conflates China and the US as countries in which LLMs are built with the corpus or body of text that was used in training. The creator of an LLM is the team that writes the GPT code, trains it on a body of text, and creates a UI to allow prediction or other output. The "ideology" in those texts belongs somewhat to the people who selected the…”

Large Language Models Reflect the Ideology of Their Creators原评论 ↗
被提交为 story · 2 次