Cross-sectional analysis of large language models in current natural language generation challenges
• Longitudinal analysis of 5 large language model families and their versions over time. • Newer model versions and larger size do not always improve task-specific capabilities. • Expert-set thresholds enable accurate evaluation of responses for each research gap. • Analysis method is reproducible and adaptable to other languages and available models.
Authors
- Elena Lloret (ORCID: https://orcid.org/0000-0002-2926-294X)
- María Miró Maestre (ORCID: https://orcid.org/0000-0001-7996-4440)
- Iván Martínez-Murillo (ORCID: https://orcid.org/0009-0007-5684-0083)
- Aitana Morote Martínez
Institutions
- University of Alicante (ES)
Publication Details
- Journal
- Information Processing & Management
- Published
- 2026-05-22
- DOI
- https://doi.org/10.1016/j.ipm.2026.104922
- Primary Topic
- Topic Modeling
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Ministerio de Ciencia, Innovación y Universidades
- Generalitat Valenciana
- Ministerio de Asuntos Económicos y Transformación Digital, Gobierno de España
- European Regional Development Fund