Geopolitical parallax: beyond Walter Lippmann just after large language models

Basit Öğe Kaydı
dc.authorid0000-0003-1677-9496
dc.authorid0009-0008-6010-6452
dc.contributor.authorYavuz, Mehmet Canen_US
dc.contributor.authorKabir, Humza Goharen_US
dc.contributor.authorÖzkan, Aylinen_US
dc.date.accessioned2025-11-21T11:32:01Z
dc.date.available2025-11-21T11:32:01Z
dc.date.issued2025-08-27
dc.departmentIşık Üniversitesi, Mühendislik ve Doğa Bilimleri Fakültesi, Bilgisayar Mühendisliği Bölümüen_US
dc.departmentIşık University, Faculty of Engineering and Natural Sciences, Department of Computer Engineeringen_US
dc.departmentIşık Üniversitesi, Lisansüstü Eğitim Enstitüsü, Bilgisayar Mühendisliği Yüksek Lisans Programıen_US
dc.departmentIşık University, School of Graduate Studies, Master’s Program in Computer Engineeringen_US
dc.description.abstractObjectivity in journalism has long been contested, oscillating between ideals of neutral, fact-based reporting and the inevitability of subjective framing. With the advent of large language models (LLMs), these tensions are now mediated by algorithmic systems whose training data and design choices may themselves embed cultural or ideological biases. This study investigates geopolitical parallax—systematic divergence in news quality and subjectivity assessments—by comparing articlelevel embeddings from Chinese-origin (Qwen, BGE, Jina) and Western-origin (Snowflake, Granite) model families. We evaluate both on a human-annotated news quality benchmark spanning fifteen stylistic, informational, and affective dimensions, and on parallel corpora covering politically sensitive topics, including Palestine and reciprocal China–United States coverage. Using logistic regression probes and matched-topic evaluation, we quantify per-metric differences in predicted positive-class probabilities between model families. Our findings reveal consistent, nonrandom divergences aligned with model origin. In Palestinerelated coverage, Western models assign higher subjectivity and positive emotion scores, while Chinese models emphasize novelty and descriptiveness. Cross-topic analysis shows asymmetries in structural quality metrics—Chinese-on-US scoring notably lower in fluency, conciseness, technicality, and overall quality—contrasted by higher negative emotion scores. These patterns align with media bias theory and our distinction between semantic, emotional, and relational subjectivity, and extend LLM bias literature by showing that geopolitical framing effects persist in downstream quality assessment tasks. We conclude that LLMbased media evaluation pipelines require cultural calibration to avoid conflating content differences with model-induced bias.en_US
dc.description.versionPreprint's Versionen_US
dc.identifier.citationYavuz, M. C., Kabir, H. G. & Özkan, A. (2025). Geopolitical parallax: beyond Walter Lippmann just after large language models. Arxiv, 1-7. doi:https://www.arxiv.org/abs/2508.19492v1en_US
dc.identifier.endpage7
dc.identifier.startpage1
dc.identifier.urihttps://hdl.handle.net/11729/6790
dc.identifier.urihttps://www.arxiv.org/abs/2508.19492v1
dc.identifier.wosPPRN:159203590
dc.identifier.wosqualityN/A
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakPreprint Citation Indexen_US
dc.institutionauthorYavuz, Mehmet Canen_US
dc.institutionauthorKabir, Humza Goharen_US
dc.institutionauthorid0000-0003-1677-9496
dc.institutionauthorid0009-0008-6010-6452
dc.language.isoenen_US
dc.publisherCornell Univen_US
dc.relation.ispartofArxiven_US
dc.relation.publicationcategoryÖn Baskı – Uluslararası – Kurum Öğretim Elemanıen_US
dc.relation.publicationcategoryÖn Baskı – Uluslararası – Öğrencien_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectArticle embeddingsen_US
dc.subjectSubjectivity detectionen_US
dc.subjectGeopolitical parallaxen_US
dc.subjectNews quality assessmenten_US
dc.subjectNatural language processingen_US
dc.subjectBias in language modelsen_US
dc.subjectContent classificationen_US
dc.subjectEthical NLPen_US
dc.titleGeopolitical parallax: beyond Walter Lippmann just after large language modelsen_US
dc.typePreprinten_US
dspace.entity.typePublicationen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim
İsim:
Geopolitical_parallax_beyond_Walter_Lippmann_just_after_large_language_models.pdf
Boyut:
523.82 KB
Biçim:
Adobe Portable Document Format
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.17 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Makale Koleksiyonu | Bilgisayar Mühendisliği Bölümü
Lisansüstü Eğitim Enstitüsü Diğer Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu