Aligning Large Language Models with Diverse Political Viewpoints
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916422638108672 |
|---|---|
| author | Stammbach, Dominik Widmer, Philine Cho, Eunjung Gulcehre, Caglar Ash, Elliott |
| author_facet | Stammbach, Dominik Widmer, Philine Cho, Eunjung Gulcehre, Caglar Ash, Elliott |
| contents | Large language models such as ChatGPT exhibit striking political biases. If users query them about political information, they often take a normative stance. To overcome this, we align LLMs with diverse political viewpoints from 100,000 comments written by candidates running for national parliament in Switzerland. Models aligned with this data can generate more accurate political viewpoints from Swiss parties, compared to commercial models such as ChatGPT. We also propose a procedure to generate balanced overviews summarizing multiple viewpoints using such models. The replication package contains all code and data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_14155 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Aligning Large Language Models with Diverse Political Viewpoints Stammbach, Dominik Widmer, Philine Cho, Eunjung Gulcehre, Caglar Ash, Elliott Computation and Language Large language models such as ChatGPT exhibit striking political biases. If users query them about political information, they often take a normative stance. To overcome this, we align LLMs with diverse political viewpoints from 100,000 comments written by candidates running for national parliament in Switzerland. Models aligned with this data can generate more accurate political viewpoints from Swiss parties, compared to commercial models such as ChatGPT. We also propose a procedure to generate balanced overviews summarizing multiple viewpoints using such models. The replication package contains all code and data. |
| title | Aligning Large Language Models with Diverse Political Viewpoints |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2406.14155 |