Philine Widmer


2024

pdf bib
Aligning Large Language Models with Diverse Political Viewpoints
Dominik Stammbach | Philine Widmer | Eunjung Cho | Caglar Gulcehre | Elliott Ash
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing

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.