Metraipolis › archive › dc_f92565909704

The Future of Natural Language Generation in the Age of Large Language Models (2026) · DOI 10.3384/nejlt.2000-1533.2026.6529

Source
Metraipolis archive
Original
https://doi.org/10.3384/nejlt.2000-1533.2026.6529
License (as archived)
CC-BY-4.0
Archived
2026-10-08T02:39:58.249Z
SHA-256 of the archived text
d4392f808f62ba32c1693ed83e629599fdc58ee9ba409d5090c45c4df699804a
Stable URL of this page
https://metraipolis.com/documento/dc_f92565909704

How to cite

The Future of Natural Language Generation in the Age of Large Language Models (2026) · DOI 10.3384/nejlt.2000-1533.2026.6529 — Metraipolis archive, https://doi.org/10.3384/nejlt.2000-1533.2026.6529 (CC-BY-4.0); archived copy: https://metraipolis.com/documento/dc_f92565909704 (Metraipolis archive dc_f92565909704, sha256 d4392f808f62ba32c1693ed83e629599fdc58ee9ba409d5090c45c4df699804a)
BibTeX
@misc{dcf92565909704,
  title = {The Future of Natural Language Generation in the Age of Large Language Models (2026) · DOI 10.3384/nejlt.2000-1533.2026.6529},
  howpublished = {Metraipolis archive},
  url = {https://doi.org/10.3384/nejlt.2000-1533.2026.6529},
  note = {License CC-BY-4.0; archived copy https://metraipolis.com/documento/dc_f92565909704; sha256 d4392f808f62ba32c1693ed83e629599fdc58ee9ba409d5090c45c4df699804a},
  year = {2026}
}

Archived text

Reproduced under CC-BY-4.0. Attribution: Metraipolis archive, https://doi.org/10.3384/nejlt.2000-1533.2026.6529. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Articolo recente con licenza aperta: scheda dai metadati Crossref (journal-article).
Titolo: The Future of Natural Language Generation in the Age of Large Language Models
Autori: Eduardo Calò, Saad Mahamood
Pubblicato: 2026-10-02 · in: Northern European Journal of Language Technology · editore: Linkoping University Electronic Press
DOI: https://doi.org/10.3384/nejlt.2000-1533.2026.6529
Licenza dell'articolo: CC-BY-4.0

Abstract (testo degli autori, CC-BY-4.0):
Natural language generation (NLG) research has focused in the past on mainly two aspects: (i) the process of language generation in itself (e.g., to give theoretical insights into models of human language) and (ii) the use of such approaches to solve applied problems (e.g., generation of medical reports, weather forecasts, etc.). Since the advent of large language models (LLMs), given their "generation capabilities", there has been a tendency among researchers to use LLMs for an increasing number of novel tasks. The use of LLMs raises questions for NLG researchers about which tasks, both theoretical and practical, are still considered NLG tasks per se, and which are still relevant, given that LLMs have solved many former problems in language generation. Through a structured literature search, we investigate domain shift in NLG before and after LLMs and discuss the positive and negative aspects that arise from this, with the aim of providing researchers with greater clarity on where we stand as a field.

Fonte: https://api.crossref.org/works/10.3384%2Fnejlt.2000-1533.2026.6529 — metadati Crossref, consultati il 2026-10-07. Interrogazione: «code generation language models».