Aligning Large Language Models with Diverse Political Viewpoints
Abstract: Large language models such as ChatGPT often exhibit striking political biases. If users query them about political information, they might take a normative stance and reinforce such biases. To overcome this, we align LLMs with diverse political viewpoints from 100,000 comments written by candidates running for national parliament in Switzerland. Such aligned models are able to generate more accurate political viewpoints from Swiss parties compared to commercial models such as ChatGPT. We also propose a procedure to generate balanced overviews from multiple viewpoints using such models.
Paper Type: Short
Research Area: Language Modeling
Research Area Keywords: model bias, policy and governance, alignment, language modeling
Contribution Types: NLP engineering experiment
Languages Studied: German, French, Italian
Submission Number: 1545
Loading