Metraipolis › archive › dc_79c63c6eef67

SMALL LANGUAGE MODELS FOR MULTILINGUAL DISINFORMATION RETRIEVAL (2026) · DOI 10.18372/2310-5461.71.21448

Source
Metraipolis archive
Original
https://doi.org/10.18372/2310-5461.71.21448
License (as archived)
CC-BY-4.0
Archived
2026-10-08T01:23:25.266Z
SHA-256 of the archived text
682be6aa1efe2524fce6cdd5966304b0017d36a6129dc514d7132f8fd627c169
Stable URL of this page
https://metraipolis.com/documento/dc_79c63c6eef67

How to cite

SMALL LANGUAGE MODELS FOR MULTILINGUAL DISINFORMATION RETRIEVAL (2026) · DOI 10.18372/2310-5461.71.21448 — Metraipolis archive, https://doi.org/10.18372/2310-5461.71.21448 (CC-BY-4.0); archived copy: https://metraipolis.com/documento/dc_79c63c6eef67 (Metraipolis archive dc_79c63c6eef67, sha256 682be6aa1efe2524fce6cdd5966304b0017d36a6129dc514d7132f8fd627c169)
BibTeX
@misc{dc79c63c6eef67,
  title = {SMALL LANGUAGE MODELS FOR MULTILINGUAL DISINFORMATION RETRIEVAL (2026) · DOI 10.18372/2310-5461.71.21448},
  howpublished = {Metraipolis archive},
  url = {https://doi.org/10.18372/2310-5461.71.21448},
  note = {License CC-BY-4.0; archived copy https://metraipolis.com/documento/dc_79c63c6eef67; sha256 682be6aa1efe2524fce6cdd5966304b0017d36a6129dc514d7132f8fd627c169},
  year = {2026}
}

Archived text

Reproduced under CC-BY-4.0. Attribution: Metraipolis archive, https://doi.org/10.18372/2310-5461.71.21448. 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: SMALL LANGUAGE MODELS FOR MULTILINGUAL DISINFORMATION RETRIEVAL
Autori: Oleh Melnychuk
Pubblicato: 2026-09-10 · in: Science-based technologies · editore: State University "Kyiv Aviation Institute"
DOI: https://doi.org/10.18372/2310-5461.71.21448
Licenza dell'articolo: CC-BY-4.0

Abstract (testo degli autori, CC-BY-4.0):
Disinformation campaigns reuse known narratives while changing the language, actors, and publication context. Such variation makes it difficult for analysts to connect new material with cases already documented by fact-checkers. To address this task, a software application was developed for multilingual narrative normalization and the retrieval of documented debunks from the EUvsDisinfo corpus. The retrieval corpus contains 7,538 fact-checking records published between 2015 and 2026. Each record links a disinformation claim to its debunk or a contextual explanation. The experiment covered materials concerning Russia’s war against Ukraine, Russia–NATO relations, Syria, and COVID-19. Across these data, the same semantic patterns recur in different languages and event contexts. The language model converts an input text into a concise narrative query. It retains the main claim and the source’s position while removing names, dates, and other contextual details. The system uses the resulting query for semantic retrieval and corpus record reranking. This module can operate as part of a disinformation-monitoring system: it connects new material with known narratives and passes the retrieved debunks to an evidence-verification component. The study compares the capabilities of the commercial large language model Gemini Flash 3.5 with the locally deployed Qwen3-4B and MamayLM-Gemma-3-4B models. The results confirm that small language models can perform narrative normalization in a multilingual retrieval system with a moderate reduction in quality compared with the commercial model. Local deployment provides control over data and enables fine-tuning to improve model quality and stability.

Fonte: https://api.crossref.org/works/10.18372%2F2310-5461.71.21448 — metadati Crossref, consultati il 2026-10-07. Interrogazione: «small language models».