When Neutral Summaries Are Not That Neutral: Quantifying Political Neutrality in LLM-Generated News Summaries (Student Abstract)
Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (28) · 29514-29516
DOI: 10.1609/aaai.v39i28.35308 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Supriti Vijay und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).
Abstract (Originalsprache)
In an era where societal narratives are increasingly shaped by algorithmic curation, investigating the political neutrality of LLMs is an important research question. This study presents a fresh perspective on quantifying the political neutrality of LLMs through the lens of abstractive text summarization of polarizing news articles. We consider five pressing issues in current US politics: abortion, gun control/rights, healthcare, immigration, and LGBTQ+ rights. Via a substantial corpus of 20,344 news articles, our study reveals a consistent trend towards pro-Democratic biases in several well-known LLMs, with gun control and healthcare exhibiting the most pronounced biases (max polarization differences of -9.49% and -6.14%, respectively). Further analysis uncovers a strong convergence in the vocabulary of the LLM outputs for these divisive topics (55% overlap for Democrat-leaning representations, 52% for Republican). Being months away from a US election of consequence, we consider our findings important.
Zitieren
APA
Vijay, S., Priyanshu, A., & KhudaBukhsh, A. R. (2025). When Neutral Summaries Are Not That Neutral: Quantifying Political Neutrality in LLM-Generated News Summaries (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 39(28), 29514-29516. https://doi.org/10.1609/aaai.v39i28.35308
Vancouver
Vijay S, Priyanshu A, KhudaBukhsh AR. When Neutral Summaries Are Not That Neutral: Quantifying Political Neutrality in LLM-Generated News Summaries (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(28):29514-29516. doi:10.1609/aaai.v39i28.35308
BibTeX
@article{Vijay2025,
author = {Vijay, Supriti and Priyanshu, Aman and KhudaBukhsh, Ashiqur R.},
title = {When Neutral Summaries Are Not That Neutral: Quantifying Political Neutrality in LLM-Generated News Summaries (Student Abstract)},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2025},
volume = {39},
number = {28},
pages = {29514--29516},
doi = {10.1609/aaai.v39i28.35308}
}
EUVIMED