Metraipolis › archive › dc_00cc7fa3f09a
Zero-shot narrative detection in social messaging — arXiv:2609.17310
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.17310
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T19:19:29.747Z
- SHA-256 of the archived text
a80bf0eb307d1bab542dfec267800acc265143f1194278223ab9f4882bbf27dc- Stable URL of this page
https://metraipolis.com/documento/dc_00cc7fa3f09a
How to cite
Zero-shot narrative detection in social messaging — arXiv:2609.17310 — arXiv (en), https://arxiv.org/abs/2609.17310 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_00cc7fa3f09a (Metraipolis archive dc_00cc7fa3f09a, sha256 a80bf0eb307d1bab542dfec267800acc265143f1194278223ab9f4882bbf27dc)
BibTeX
@misc{dc00cc7fa3f09a,
title = {Zero-shot narrative detection in social messaging — arXiv:2609.17310},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.17310},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_00cc7fa3f09a; sha256 a80bf0eb307d1bab542dfec267800acc265143f1194278223ab9f4882bbf27dc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.17310. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
This study investigates the zero-shot ability of large language models (LLMs) to identify and classify hidden narratives in social messages. Our research hypothesis is that LLMs' extensive contextual knowledge allows them to interpret messages on a deeper, pragmatic level, going beyond basic sentiment or topic analysis. Experiments on the Dipromats and SemEval datasets show that providing models with human-written narrative descriptions significantly improves performance, without the need of training examples. In contrast, automatically generated descriptions or the use of few examples (few-shot) often degrade accuracy due to subtle shifts in framing. The study also finds that ensemble methods, particularly majority voting, enhance robustness and that larger models perform best while also being less sensitive to prompt variations. The findings validate that LLMs can effectively detect strategic narratives in a zero-shot setting, and when combined with simple ensembling and human-written descriptions, they can rival supervised systems, offering a scalable solution for narrative detection, specially when there is no training data for the vast majority of domains. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.17310 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-15T18:32:32.868Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).