Generative artificial intelligence and local media: An analysis of territorial bias in five language models
Article Sidebar
Main Article Content
The development of large language models (LLMs) has transformed the processes of information search and access in digital environments. This study examines how five LLMs (ChatGPT, Claude, Gemini, Copilot, and Perplexity) respond to queries about media-related cases that occurred in the Basque Country between 2023 and 2025, as well as to general questions on current affairs at local, regional, and national levels. The methodology was based on the use of prompts applied under controlled technical conditions, with responses evaluated in terms of length, source citation, traceability, and territorial contextualisation. The findings reveal that ChatGPT and Perplexity offer the most extensive, traceable, and contextually rich responses, while Claude and Gemini display notable opacity and limited regional coverage. A systematic tendency to prioritise national media is observed, even in queries concerning local and regional issues, thereby limiting informational diversity. These differences are not merely technical but structural, stemming from corpus design, retrieval architecture, and licensing agreements between media outlets and developers, which together create a territorial information gap in the use of generative AI.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
(c) Barbara Sarrionandia, Simón Peña-Fernández, Jesús-Ángel Pérez-Dasilva, 2025
Copyright
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0).
Barbara Sarrionandia, Universidad del País Vasco / Euskal Herriko Unibertsitatea
Barbara Sarrionandia holds a degree in Journalism from the University of Navarra and a Master's Degree in Secondary Education, specialising in Geo-graphy and History, from the International University of La Rioja (UNIR). Her research focuses on artificial intelligence, disinformation, and media lite-racy. Over the past two decades, she has developed her professional career in media and institutions at both national and international levels.
Simón Peña-Fernández, Universidad del País Vasco / Euskal Herriko Unibertsitatea
Simón Peña-Fernández is Full Professor in the Department of Journalism at the University of the Basque Country (UPV/EHU). His main areas of research are cyberjournalism, digital communication, and artificial intelligence. Together with Koldobika Meso, he is Principal Investigator of the research project “The Impact of Artificial Intelligence and Algorithms on Digital Media, Professionals, and Audiences” (PID2022-138391OB-I00), funded by the Spanish Ministry of Science and Innovation.
Jesús-Ángel Pérez-Dasilva, Universidad del País Vasco / Euskal Herriko Unibertsitatea
Jesús Ángel Pérez-Dasilva is Full Professor in the Department of Journalism at the University of the Basque Country (UPV/EHU). His research interests include cyberjournalism, social communication, social media, and social innovation. He is Principal Investigator of the project “The Impact of Artificial Intelligence on Basque Media and Media Professionals” (US 23/10), funded by the UPV/EHU
Agarwal, U., Tanmay, K., Khandelwal, A. y Choudhury, M. (2024). Ethical Reasoning and Moral Value Alignment of LLMs Depend on the Language we Prompt them in. arXiv. https://doi.org/10.48550/arxiv.2404.18460
Ai, Q., Bai, T., Cao, Z., Chang, Y., Chen, J., Chen, Z., Cheng, Z., Dong, S., Dou, Z., Feng, F., Gao, S., Guo, J., He, X., Lan, Y., Li, C., Liu, Y., Lyu, Z., Ma, W., Ma, J., ... Zhu, X. (2023). Information Retrieval Meets Large Language Models: A Strategic Report from Chinese IR Community. arXiv. https://doi.org/10.48550/arxiv.2307.09751
Algaba, A., Mazijn, C., Holst, V., Tori, F., Wenmackers, S. y Ginis, V. (2024). Large Language Models Reflect Human Citation Patterns with a Heightened Citation Bias. arXiv. https://doi.org/10.48550/arxiv.2405.15739
Amirizaniani, M. yao, J., Lavergne, A., Okada, E. S., Chadha, A., Roosta, T. y Shah, C. (2024a). LLMAuditor: A Framework for Auditing Large Language Models Using Human-in-the-Loop. arXiv. https://doi.org/10.48550/arxiv.2402.09346
Amirizaniani, M., Roosta, T., Chadha, A. y Shah, C. (2024b). AuditLLM: A Tool for Auditing Large Language Models Using Multiprobe Approach. arXiv. https://doi.org/10.48550/arxiv.2402.09334
Anagnostidis, S. y Bulian, J. (2024). How Susceptible are LLMs to Influence in Prompts? arXiv. https://doi.org/10.48550/arXiv.2408.11865
Artero-Muñoz, J. P., Zugasti, R. y Hernández-Corchete, S. (2021). Media concentration in Spain: National, sectorial, and regional groups. Estudios Sobre el Mensaje Periodístico, 27(3), 765–777. https://doi.org/10.5209/esmp.72928
Baryshnikov, P. N. (2024). What is scientific knowledge produced by Large Language Models? Philosophical Problems Of IT y Cyberspace (PhilIT&C), 1, 89-103. https://doi.org/10.17726/philit.2024.1.6
Blázquez-Ruiz, F. J. (2022). Paradoja de la transparencia en la IA. Revista Internacional de Pensamiento Político, 17, 261-272. https://doi.org/10.46661/revintpensampolit.7526
Caro-González, F. J., Gordillo, M. G. y Valencia, O. B. (2025). Concentración y desiertos de noticias: el mapa informativo andaluz. Revista CENTRA de Ciencias Sociales, 4(1). https://doi.org/10.54790/rccs.93
Castillo-Eslava, F., Mougan, C., Romero-Eche, A. y Staab, S. (2023). The Role of Large Language Models in the Recognition of Territorial Sovereignty. arXiv. https://doi.org/10.48550/arxiv.2304.06030
Chang, Y., Wang, X., Wang, J., Wu, Y. yang, L., Zhu, K., Chen, H. yi, X., Wang, C., Wang, Y. ye, W., Zhang, Y., Chang, Y. yu, P. S. yang, Q. y Xie, X. (2024). A Survey on Evaluation of Large Language Models. ACM Transactions On Intelligent Systems And Technology, 15(3), 1–45. https://doi.org/10.1145/3641289
Charles, D. D., Mogoutov, A. y Baumard, N. (2024). Towards Transparency: Exploring LLM Trainings Datasets through Visual Topic Modeling and Semantic Frame. arXiv. https://doi.org/10.48550/arxiv.2406.06574
Chelli, M., Descamps, J., Lavoué, V., Trojani, C., Azar, M., Deckert, M., et al. (2024). Hallucination Rates and Reference Accuracy of ChatGPT and Bard for Systematic Reviews: Comparative Analysis. Journal Of Medical Internet Research, 26, e53164. https://doi.org/10.2196/53164
Chiang, C. y Lee, H. (2024). Merging Facts, Crafting Fallacies: Evaluating the Contradictory Nature of Aggregated Factual Claims in Long-Form Generations. arXiv. https://doi.org/10.48550/arxiv.2402.05629
Chiang, W., Zheng, L., Sheng, Y., Angelopoulos, A. N., Li, T., Li, D., Zhang, H., Zhu, B., Jordan, M., Gonzalez, J. E. y Stoica, I. (2024). Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference. arXiv. https://doi.org/10.48550/arxiv.2403.04132
Choenni, R. y Shutova, E. (2024). Self-Alignment: Improving Alignment of Cultural Values in LLMs via In-Context Learning. arXiv. https://doi.org/10.48550/arxiv.2408.16482
Cuéllar-Rodríguez, A. (2023). Epistemology and ontology in Science: the challenge of Artificial Intelligence. Anales de la Real Academia Nacional de Farmacia, 89(03), 379–386. https://doi.org/10.53519/analesranf.2023.89.03.09
Dierickx, L., Lindén, C. y Opdahl, A. L. (2023). The Information Disorder Level (IDL) Index: A Human-Based Metric to Assess the Factuality of Machine-Generated Content. En D. Ceolin, T. Caselli y M. Tulin (eds.), Disinformation in Open Online Media. MISDOOM 2023 (pp. 60-71). https://doi.org/10.1007/978-3-031-47896-3_5
Duan, S. yi, X., Zhang, P., Lu, T., Xie, X. y Gu, N. (2023). Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning. arXiv. https://doi.org/10.48550/arxiv.2310.11053
Esteban, J. L. G. (2014). La transformación del ecosistema mediático español: el caso de eldiario.es. Revista Mediterránea de Comunicación, 5(2), 159. https://doi.org/10.14198/medcom2014.5.2.10
Franganillo, J. (2023). La inteligencia artificial generativa y su impacto en la creación de contenidos mediáticos. Methaodos Revista de Ciencias Sociales, 11(2), m231102a10. https://doi.org/10.17502/mrcs.v11i2.710
Gabriel, S., Celikyilmaz, A., Jha, R., Choi, Y. y Gao, J. (2020). GO FIGURE: A meta evaluation of factuality in summarization. arXiv. https://arxiv.org/abs/2010.12834
Gao, Y., Baptista-Hon, D. T. y Zhang, K. (2023). The inevitable transformation of medicine and research by large language models. MedComm – Future Medicine, 2(2). https://doi.org/10.1002/mef2.49
García-Santamaría, J. V. y Pérez-Serrano, M. J. (2020). Grupos de comunicación en España: madurez y profundas transformaciones en un final de ciclo. Palabra Clave, 23(4), 1–32. https://doi.org/10.5294/pacla.2020.23.4.5
Ghodratnama, S. y Zakershahrak, M. (2023). Adapting LLMs for Efficient, Personalized Information Retrieval: Methods and Implications. arXiv. https://doi.org/10.48550/arxiv.2311.12287
Guo, Z., Jin, R., Liu, C., Huang, Y., Shi, D., Supryadi, Yu, L., Liu, Y., Li, J., Xiong, B. y Xiong, D. (2023). Evaluating Large Language Models: A Comprehensive Survey. arXiv. https://doi.org/10.48550/arxiv.2310.19736
Hadar-Shoval, D., Asraf, K., Mizrachi, Y., Haber, Y. y Elyoseph, Z. (2024). Assessing the Alignment of Large Language Models With Human Values for Mental Health Integration: Cross-Sectional Study Using Schwartz’s Theory of Basic Values. JMIR Mental Health, 11, e55988. https://doi.org/10.2196/55988
Harandizadeh, B., Salinas, A. y Morstatter, F. (2024). Risk and Response in Large Language Models: Evaluating Key Threat Categories. arXiv. https://doi.org/10.48550/arxiv.2403.14988
Hida, R., Kaneko, M. y Okazaki, N. (2024). Social Bias Evaluation for Large Language Models Requires Prompt Variations. arXiv. https://doi.org/10.48550/arxiv.2407.03129
Huang, L., et al. (2023). A Survey on Hallucination in Large Language Models. ACM Transactions On Office Information Systems. https://doi.org/10.1145/3703155
Jiao, J., Afroogh, S., Xu, Y. y Phillips, C. (2024). Navigating LLM Ethics: Advancements, Challenges, and Future Directions. arXiv. https://doi.org/10.48550/arxiv.2406.18841
Larrondo-Ureta, A. y Peña-Fernández, S. (2024). La formación de periodistas en la era de la inteligencia artificial: aproximaciones desde la epistemología de la comunicación. Anuario ThinkEPI, 18. https://doi.org/10.3145/thinkepi.2024.e18a11
Liang, Y., Xiao, J., Gan, W. y Yu, P. S. (2024). Watermarking Techniques for Large Language Models: A Survey. arXiv. https://doi.org/10.48550/arxiv.2409.00089
Lin, Y. y Chen, Y. (2023). LLM-Eval: Unified Multi-Dimensional Automatic Evaluation for Open-Domain Conversations with Large Language Models. arXiv. https://doi.org/10.48550/arxiv.2305.13711
Lindemann, N. F. (2023). Sealed knowledges: A critical approach to the usage of LLMs as search engines. En Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society (pp. 985-986). https://doi.org/10.1145/3600211.3604737
Liu, G., Wang, X. yuan, L., Chen, Y. y Peng, H. (2023a). Prudent Silence or Foolish Babble? Examining Large Language Models’ Responses to the Unknown. arXiv. https://doi.org/10.48550/arxiv.2311.09731
Liu, N. F., Zhang, T. y Liang, P. (2023b). Evaluating Verifiability in Generative Search Engines. arXiv. https://doi.org/10.48550/arxiv.2304.09848
Liu, Y., Cao, J., Liu, C., Ding, K. y Jin, L. (2024). Datasets for Large Language Models: A Comprehensive Survey. arXiv. https://doi.org/10.48550/arxiv.2402.18041
Luitse, D. y Denkena, W. (2021). The Great Transformer: Examining the Role of Large Language Models in the Political Economy of AI. Big Data y Society, 8(2). https://doi.org/10.1177/20539517211047734
Masís-González, T. M. (2024). La metáfora del shoggoth en la inteligencia artificial. Pensamiento Actual, 24(43). https://doi.org/10.15517/pa.v24i43.62864
Masud, S., Singh, S., Hangya, V., Fraser, A. y Chakraborty, T. (2024). Hate Personified: Investigating the role of LLMs in content moderation. arXiv. https://doi.org/10.48550/arxiv.2410.02657
McGowan, A., Gui, Y., Dobbs, M., Shuster, S., Cotter, M., Selloni, A., et al. (2023). ChatGPT and Bard exhibit spontaneous citation fabrication during psychiatry literature search. Psychiatry Research, 326, 115334. https://doi.org/10.1016/j.psychres.2023.115334
Menick, J., Trebacz, M., Mikulik, V., Aslanides, J., Song, F., Chadwick, M., et al. (2022). Teaching language models to support answers with verified quotes. arXiv. https://doi.org/10.48550/arxiv.2203.11147
Mihajlov-Prokopović, A., Jevtović, Z. y Jovanović, Z. (2019). Digital challenges of local media of the Nišava District. CM: Communication and Media, 14(46), 5–32. https://doi.org/10.5937/cm14-24293
Mokander, J., Schuett, J., Kirk, H. R. y Floridi, L. (2023). Auditing large language models: a three-layered approach. AI And Ethics, 4(4), 1085–1115. https://doi.org/10.1007/s43681-023-00289-2
Morato, O. y Nunes, D. J. C. (2023). O uso do design comportamental nas plataformas tecnológicas e as iniciativas de sua regulamentação: Um estudo do modelo gancho. Revista Justiça Do Direito, 37(2). https://doi.org/10.5335/rjd.v37i2.14961
Muhlgay, D., Ram, O., Magar, I., Levine, Y., Ratner, N., Belinkov, Y., et al. (2023). Generating benchmarks for factuality evaluation of language models. arXiv. https://doi.org/10.48550/arxiv.2307.06908
Muñoz-Vela, J. M. (2024). Inteligencia artificial generativa. Desafíos para la propiedad intelectual. Revista de Derecho de la UNED, (33), 17–75. https://doi.org/10.5944/rduned.33.2024.41924
Negreira-Rey, M., Vázquez-Herrero, J. y López-García, X. (2023). No people, no news: News deserts and areas at risk in Spain. Media and Communication, 11(3), 126–138. https://doi.org/10.17645/mac.v11i3.6727
Novelli, C., Casolari, F., Hacker, P., Spedicato, G. y Floridi, L. (2024). Generative AI in EU Law: Liability, Privacy, Intellectual Property, and Cybersecurity. Computer Law y Security Review, 55, 106066. https://doi.org/10.1016/j.clsr.2024.106066
Olsen, R. y Hess, K. (2024). “It’s New to Us”: Exploring Authentic Innovation in Local News Settings. Media and Communication, 12, 7444. https://doi.org/10.17645/mac.7444
Patil, R. y Gudivada, V. (2024). A Review of Current Trends, Techniques, and Challenges in Large Language Models (LLMs). Applied Sciences, 14(5), 2074. https://doi.org/10.3390/app14052074
Peña-Fernández, S., Peña-Alonso, U. y Eizmendi-Iraola, M. (2023). El discurso de los periodistas sobre el impacto de la inteligencia artificial generativa en la desinformación. Estudios Sobre el Mensaje Periodístico, 29(4), 833–841. https://doi.org/10.5209/esmp.88673
Pezeshkpour, P. y Hruschka, E. (2023). Large Language Models Sensitivity to The Order of Options in Multiple-Choice Questions. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2308.11483
Piedra-Alegría, J. (2023). Anotaciones iniciales para una reflexión ética sobre la regulación de la Inteligencia Artificial en la Unión Europea. Revista de Derecho, 28, e3264. https://doi.org/10.22235/rd28.3264
Pit, P., Ma, X., Conway, M., Chen, Q., Bailey, J., Pit, H., Keo, P., Diep, W. y Jiang, Y. (2024). Whose Side Are You On? Investigating the Political Stance of Large Language Models. arXiv. https://doi.org/10.48550/arxiv.2403.13840
Rastogi, C., Ribeiro, M. T., King, N., Nori, H. y Amershi, S. (2023). Supporting human-AI collaboration in auditing LLMs with LLMs. En Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society, 913–926. https://doi.org/10.1145/3600211.3604712
Richter, L., He, X., Minervini, P. y Kusner, M. J. (2024). An Auditing Test To Detect Behavioral Shift in Language Models. arXiv. https://doi.org/10.48550/arxiv.2410.19406
Rotaru, G., Anagnoste, S. y Oancea, V. (2024). How Artificial Intelligence Can Influence Elections: Analyzing the Large Language Models (LLMs) Political Bias. En Proceedings of the International Conference on Business Excellence, 18(1), 1882–1891. https://doi.org/10.2478/picbe-2024-0158
Röttger, P., Hofmann, V., Pyatkin, V., Hinck, M., Kirk, H. R., Schütze, H. y Hovy, D. (2024). Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models. arXiv. https://doi.org/10.48550/arxiv.2402.16786
Sarkar, D. (2024). Navigating the Knowledge Sea: Planet-scale answer retrieval using LLMs. arXiv. https://doi.org/10.48550/arxiv.2402.05318
Schwartz, I. S., Link, K. E., Daneshjou, R. y Cortés-Penfield, N. (2023). Black box warning: Large language models and the future of infectious diseases consultation. Clinical Infectious Diseases, 78(4), 860–866. https://doi.org/10.1093/cid/ciad633
Shao, M., Basit, A., Karri, R. y Shafique, M. (2024). Survey of different Large Language Model Architectures: Trends, Benchmarks, and Challenges. IEEE Access, 12, 188664-188706. https://doi.org/10.1109/access.2024.3482107
Silveira, S. A. (2020). Responsabilidade algorítmica, personalidade eletrônica e democracia. Revista Eletrônica Internacional de Economia Política da Informação da Comunicação e da Cultura, 22(2), 83–96. https://periodicos.ufs.br/eptic/article/view/12021
Sun, D. Q., Abzaliev, A., Kotek, H., Xiu, Z., Klein, C. y Williams, J. D. (2023). DELPHI: Data for Evaluating LLMs’ Performance in Handling Controversial Issues. arXiv. https://doi.org/10.48550/arxiv.2310.18130
Tlaie, A. (2024). Exploring and Steering the Moral Compass of Large Language Models. arXiv. https://doi.org/10.48550/arxiv.2405.17345
Vara-Miguel, A., Sánchez-Blanco, C., Chalezquer, C. S. S. y Negredo, S. (2021). Funding sustainable online news: Sources of revenue in digital-native and traditional media in Spain. Sustainability, 13(20), 11328. https://doi.org/10.3390/su132011328
Wan, A., Wallace, E. y Klein, D. (2024). What evidence do language models find convincing? arXiv. https://doi.org/10.48550/arxiv.2402.11782
Wang, Y., Zhong, W., Li, L., Mi, F., Zeng, X., Huang, W., Shang, L., Jiang, X. y Liu, Q. (2023). Aligning Large Language Models with Human: A Survey. arXiv. https://doi.org/10.48550/arxiv.2307.12966
Wu, K., Wu, E., Cassasola, A., Zhang, A., Wei, K., Nguyen, T., et al. (2024). How well do LLMs cite relevant medical references? An evaluation framework and analyses. arXiv. https://doi.org/10.48550/arxiv.2402.02008
Yue, X., Wang, B., Zhang, K., Chen, Z., Su, Y. y Sun, H. (2023). Automatic Evaluation of Attribution by Large Language Models. arXiv. https://doi.org/10.48550/arxiv.2305.06311
Zhang, D., et al. (2024). A survey of datasets in medicine for large language models. Intelligence y Robotics, 4(4), 457–478. https://doi.org/10.20517/ir.2024.27
Zhao, H., et al. (2024). Towards uncovering how large language model works: An explainability perspective. arXiv. https://doi.org/10.48550/arxiv.2402.10688
Zheng, X., Wang, L., Liu, Y., Ma, X., Shen, C. y Wang, C. (2025). CALM: Curiosity-Driven Auditing for Large Language Models. arXiv. https://doi.org/10.48550/arxiv.2501.02997
Zhu, Y. yuan, H., Wang, S., Liu, J., Liu, W., Deng, C., Dou, Z. y Wen, J. (2023). Large Language Models for Information Retrieval: A Survey. arXiv. https://doi.org/10.48550/arxiv.2308.07107