Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2410.18417 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912209931599872 |
|---|---|
| author | Buyl, Maarten Rogiers, Alexander Noels, Sander Bied, Guillaume Dominguez-Catena, Iris Heiter, Edith Johary, Iman Mara, Alexandru-Cristian Romero, Raphaël Lijffijt, Jefrey De Bie, Tijl |
| author_facet | Buyl, Maarten Rogiers, Alexander Noels, Sander Bied, Guillaume Dominguez-Catena, Iris Heiter, Edith Johary, Iman Mara, Alexandru-Cristian Romero, Raphaël Lijffijt, Jefrey De Bie, Tijl |
| contents | 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'. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_18417 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Large Language Models Reflect the Ideology of their Creators Buyl, Maarten Rogiers, Alexander Noels, Sander Bied, Guillaume Dominguez-Catena, Iris Heiter, Edith Johary, Iman Mara, Alexandru-Cristian Romero, Raphaël Lijffijt, Jefrey De Bie, Tijl Computation and Language Machine Learning 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'. |
| title | Large Language Models Reflect the Ideology of their Creators |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2410.18417 |