Aligning Large Language Models with Diverse Political Viewpoints
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.
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Cross-Cutting Political Awareness through Diverse News Recommendations
The suggestions generated by most existing recommender systems are known to suffer from a lack of diversity, and other issues like popularity bias. As a result, they have been observed to promote well-known "blockbuster"…
DiversityRecommendation SystemsCan AI mediation improve democratic deliberation?
The strength of democracy lies in the free and equal exchange of diverse viewpoints. Living up to this ideal at scale faces inherent tensions: broad participation, meaningful deliberation, and political equality often tr…
PoliTune: Analyzing the Impact of Data Selection and Fine-Tuning on Economic and Political Biases in Large Language Models
In an era where language models are increasingly integrated into decision-making and communication, understanding the biases within Large Language Models (LLMs) becomes imperative, especially when these models are applie…
Decision MakingLarge Language Modelparameter-efficient fine-tuningIntegrating Large Language Models and Knowledge Graphs to Capture Political Viewpoints in News Media
News sources play a central role in democratic societies by shaping political and social discourse through specific topics, viewpoints and voices. Understanding these dynamics is essential for assessing whether the media…
Knowledge GraphsWhen Bigger Isn't Better: A Comprehensive Fairness Evaluation of Political Bias in Multi-News Summarisation
Multi-document news summarisation systems are increasingly adopted for their convenience in processing vast daily news content, making fairness across diverse political perspectives critical. However, these systems can e…