← Search

Philine Widmer

1 accepted papers

2024

Aligning Large Language Models with Diverse Political Viewpoints

EMNLP 2024main

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…