Aller au contenu principal
Profil bibliographique

Premtim Sahitaj

Informations fournies par OpenAlex. Research Africa ne déduit ni nationalité, ni poste, ni coordonnées personnelles.

41Publications signalées
93Citations signalées
2Affiliations récentes

Les institutions déclarées

Les domaines associés

Topic ModelingNatural Language Processing TechniquesMulti-Agent Systems and NegotiationMisinformation and Its ImpactsSoftware Engineering Research

Les publications récentes

Accès ouvert 2026 preprint OpenAlex

Uncovering Temporal Framing in the News

Tarek Mahmoud1, Veronika Solopova, Premtim Sahitaj, Ariana Sahitaj et autres

Temporal language does more than place events on a timeline. In news discourse, references to the past, present, and future can function as rhetorical devices that shape interpretation and persuasion. Here, we study temporal framing, defined as the persuasive use of time-related …

de, us (code pays fourni par la source)

0 citations arXiv (Cornell University)
Accès ouvert 2026 preprint OpenAlex

Fine-tuning with Hierarchical Prompting for Robust Propaganda Classification Across Annotation Schemas

Lukas Stähelin, Veronika Solopova, Max Upravitelev, David Kaplan et autres

Propaganda detection in social media is challenging due to noisy, short texts and low annotation agreements. We introduce a new intent-focused taxonomy of propaganda techniques and compare it against an established, higher-agreement schema. Along three dimensions (model portfolio, schema effects, and prompting …

0 citations arXiv (Cornell University)
Accès ouvert 2026 preprint OpenAlex

Fine-tuning with Hierarchical Prompting for Robust Propaganda Classification Across Annotation Schemas

Lukas Stähelin, Veronika Solopova, Max Upravitelev, David Kaplan et autres

Propaganda detection in social media is challenging due to noisy, short texts and low annotation agreements. We introduce a new intent-focused taxonomy of propaganda techniques and compare it against an established, higher-agreement schema. Along three dimensions (model portfolio, schema effects, and prompting …

de (code pays fourni par la source)

0 citations arXiv (Cornell University)
Accès ouvert 2026 preprint OpenAlex

From Articles to Premises: Building PrimeFacts, an Extraction Methodology and Resource for Fact-Checking Evidence

Premtim Sahitaj, Jawan Kolanowski, Ariana Sahitaj, Veronika Solopova et autres

Fact-checking articles encode rich supporting evidence and reasoning, yet this evidence remains largely inaccessible to automated verification systems due to unstructured presentation. We introduce PrimeFacts, a methodology and resource for extracting fine-grained evidence from full fact-checking articles. We compile 13,106 PolitiFact articles …

0 citations arXiv (Cornell University)
Accès ouvert 2026 conference-paper OpenAlex

Transparency as Architecture: Structural Compliance Gaps in EU AI Act Article 50 II

Vera Schmitt, Niklas Kruse, Premtim Sahitaj, Julius Schöning

Art. 50 II of the EU Artificial Intelligence Act mandates dual transparency for AI-generated content: outputs must be labeled in both human-understandable and machine-readable form for automated verification.This requirement, entering into force in August 2026, collides with fundamental constraints of current generative …

de (code pays fourni par la source)

1 citation
Accès ouvert 2026 conference-paper OpenAlex

Retrieving Climate Change Disinformation by Narrative

Max Upravitelev, Veronika Solopova, Charlott Jakob, Premtim Sahitaj et autres

Detecting climate disinformation narratives typically relies on fixed taxonomies, which do not accommodate emerging narratives.Thus, we re-frame narrative detection as a retrieval task: given a narrative's core message as a query, rank texts from a corpus by alignment with that narrative.This formulation …

de (code pays fourni par la source)

0 citations
Accès ouvert 2026 conference-paper OpenAlex

From Articles to Premises: Building PrimeFacts, an Extraction Methodology and Resource for Fact-Checking Evidence

Premtim Sahitaj, Jawan Kolanowski, Ariana Sahitaj, Veronika Solopova et autres

Fact-checking articles encode rich supporting evidence and reasoning, yet this evidence remains largely inaccessible to automated verification systems due to unstructured presentation. We introduce PrimeFacts, a methodology and resource for extracting fine-grained evidence from full fact-checking articles. We compile 13,106 PolitiFact articles …

0 citations
Accès ouvert 2026 preprint OpenAlex

Transparency as Architecture: Structural Compliance Gaps in EU AI Act Article 50 II

Vera Schmitt, Niklas Kruse, Premtim Sahitaj, Julius Schöning

Art. 50 II of the EU Artificial Intelligence Act mandates dual transparency for AI-generated content: outputs must be labeled in both human-understandable and machine-readable form for automated verification. This requirement, entering into force in August 2026, collides with fundamental constraints of current …

4 citations arXiv (Cornell University)
Accès ouvert 2026 preprint OpenAlex

Retrieving Climate Change Disinformation by Narrative

Max Upravitelev, Veronika Solopova, Charlott Jakob, Premtim Sahitaj et autres

Detecting climate disinformation narratives typically relies on fixed taxonomies, which do not accommodate emerging narratives. Thus, we re-frame narrative detection as a retrieval task: given a narrative's core message as a query, rank texts from a corpus by alignment with that narrative. …

0 citations arXiv (Cornell University)
Accès ouvert 2026 preprint OpenAlex

Multiperspectivity as a Resource for Narrative Similarity Prediction

Max Upravitelev, Veronika Solopova, Jing Yang, Charlott Jakob et autres

Predicting narrative similarity can be understood as an inherently interpretive task: different, equally valid readings of the same text can produce divergent interpretations and thus different similarity judgments, posing a fundamental challenge for semantic evaluation benchmarks that encode a single ground truth. …

0 citations arXiv (Cornell University)
Accès ouvert 2026 preprint OpenAlex

Multiperspectivity as a Resource for Narrative Similarity Prediction

Max Upravitelev, Veronika Solopova, Jing Yang, Charlott Jakob et autres

Predicting narrative similarity can be understood as an inherently interpretive task: different, equally valid readings of the same text can produce divergent interpretations and thus different similarity judgments, posing a fundamental challenge for semantic evaluation benchmarks that encode a single ground truth. …

de (code pays fourni par la source)

0 citations arXiv (Cornell University)

BNTIC News n’est pas le producteur de ces données. Les publications sont interrogées à la demande dans Crossref, OpenAIRE, DOAJ, Europe PMC, HAL, DataCite, AfricArXiv, ROR et la Banque mondiale, sans clé d’accès. OpenAlex reste optionnel. Aucun service payant n’est nécessaire et aucune donnée externe n’est enregistrée en base. Consulter les sources et leurs limites.