Mostrar o rexistro simple do ítem
Contrasting Linguistic Patterns in Human and LLM-Generated News Text
dc.contributor.author | Muñoz-Ortiz, Alberto | |
dc.contributor.author | Gómez-Rodríguez, Carlos | |
dc.contributor.author | Vilares, David | |
dc.date.accessioned | 2024-08-29T09:29:52Z | |
dc.date.available | 2024-08-29T09:29:52Z | |
dc.date.issued | 2024 | |
dc.identifier.citation | Muñoz-Ortiz, A., Gómez-Rodríguez, C. & Vilares, D. Contrasting Linguistic Patterns in Human and LLM-Generated News Text. Artif Intell Rev 57, 265 (2024). https://doi.org/10.1007/s10462-024-10903-2 | es_ES |
dc.identifier.uri | http://hdl.handle.net/2183/38751 | |
dc.description | Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG | es_ES |
dc.description | Financiado para publicación en acceso aberto: CRUE-CSIC/Springer Nature | es_ES |
dc.description | The data analyzed on this article has been obtained using the New York Times Archive API (https://developer.nytimes.com/docs/archive-product/1/overview), gathering all the available articles from the 1st of October, 2023 to the 24th of January, 2024. We released the code and the used data on: https://zenodo.org/records/11186264. | es_ES |
dc.description.abstract | [Abstract]: We conduct a quantitative analysis contrasting human-written English news text with comparable large language model (LLM) output from six different LLMs that cover three different families and four sizes in total. Our analysis spans several measurable linguistic dimensions, including morphological, syntactic, psychometric, and sociolinguistic aspects. The results reveal various measurable differences between human and AI-generated texts. Human texts exhibit more scattered sentence length distributions, more variety of vocabulary, a distinct use of dependency and constituent types, shorter constituents, and more optimized dependency distances. Humans tend to exhibit stronger negative emotions (such as fear and disgust) and less joy compared to text generated by LLMs, with the toxicity of these models increasing as their size grows. LLM outputs use more numbers, symbols and auxiliaries (suggesting objective language) than human texts, as well as more pronouns. The sexist bias prevalent in human text is also expressed by LLMs, and even magnified in all of them but one. Differences between LLMs and humans are larger than between LLMs. | es_ES |
dc.description.sponsorship | Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature. We acknowledge the European Research Council (ERC), which has funded this research under the Horizon Europe research and innovation programme (SALSA, grant agreement No 101100615); SCANNER-UDC (PID2020-113230RB-C21) funded by MICIU/AEI/10.13039/501100011033; Xunta de Galicia (ED431C 2020/11); GAP (PID2022-139308OA-I00) funded by MICIU/AEI/10.13039/501100011033/ and by ERDF, EU; Grant PRE2021-097001 funded by MICIU/AEI/10.13039/501100011033 and by ESF+ (predoctoral training grant associated to project PID2020–113230RB-C21); and Centro de Investigación de Galicia “CITIC”, funded by the Xunta de Galicia through the collaboration agreement between the Consellería de Cultura, Educación, Formación Profesional e Universidades and the Galician universities for the reinforcement of the research centres of the Galician University System (CIGUS). Funding for open access charge: Universidade da Coruña/CISUG. | es_ES |
dc.description.sponsorship | Xunta de Galicia; ED431C 2020/11 | es_ES |
dc.language.iso | eng | es_ES |
dc.publisher | Springer | es_ES |
dc.relation | info:eu-repo/grantAgreement/EC/HE/101100615 | es_ES |
dc.relation | info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/PID2020-113230RB-C21/ES/MODELOS MULTITAREA DE ETIQUETADO SECUENCIAL PARA EL RECONOCIMIENTO DE ENTIDADES ENRIQUECIDO CON INFORMACIÓN LINGÜÍSTICA: SINTAXIS E INTEGRACIÓN MULTITAREA (SCANNER-UDC) | es_ES |
dc.relation | info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023/PID2022-1393080A-100/ES/REPRESENTACIONES ESTRUCTURADAS VERDES Y ENCHUFABLES | es_ES |
dc.relation | info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023/PRE2021-097001/ES/ | es_ES |
dc.relation.uri | https://doi.org/10.1007/s10462-024-10903-2 | es_ES |
dc.rights | Attribution 4.0 International (CC BY) | es_ES |
dc.rights.uri | http://creativecommons.org/licenses/by/3.0/es/ | * |
dc.subject | Large language models | es_ES |
dc.subject | Computational linguistics | es_ES |
dc.subject | Machine-generated text | es_ES |
dc.subject | Linguistic biases | es_ES |
dc.title | Contrasting Linguistic Patterns in Human and LLM-Generated News Text | es_ES |
dc.type | info:eu-repo/semantics/article | es_ES |
dc.rights.access | info:eu-repo/semantics/openAccess | es_ES |
UDC.journalTitle | Artificial Intelligence Review | es_ES |
UDC.volume | 57 | es_ES |
UDC.issue | 265 | es_ES |
dc.identifier.doi | 10.1007/s10462-024-10903-2 |
Ficheiros no ítem
Este ítem aparece na(s) seguinte(s) colección(s)
-
OpenAIRE [355]
-
GI-LYS - Artigos [51]