Publications

5 documents

Géraud Faye, Benjamin Icard, Morgane Casanova, Guillaume Gadek, Guillaume Gravier, et al.. Reliable News or Propagandist News? A Neurosymbolic Model Using Genre, Topic, and Persuasion Techniques to Improve Robustness in Classification. Information Disorder Workshop (InDor 2026) at the 15th Conference on Computational Linguistics, Language Resources and Evaluation (LREC 2026), May 2026, Palma de Majorque, Spain. ⟨hal-05577530⟩
Benno Uthayasooriyar, Antoine Ly, Franck Vermet, Caio Corro. DocPolarBERT: A Pre-trained Model for Document Understanding with Relative Polar Coordinate Encoding of Layout Structures. EACL 2026 - 19th Conference of the European Chapter of the Association for Computational Linguistics, Association for Computational Linguistics, Mar 2026, Rabat, Morocco. pp.3897-3907. ⟨hal-05571266⟩
Ayoub Hammal, Pierre Zweigenbaum, Caio Corro. KAD: A Framework for Proxy-based Test-time Alignment with Knapsack Approximation Deferral. EACL 2026 - 19th Conference of the European Chapter of the Association for Computational Linguistics, Mar 2026, Rabat, Morocco. pp.3854-3872, ⟨10.18653/v1/2026.eacl-long.179⟩. ⟨hal-05571208⟩
Benjamin Icard, Thomas Girault, Géraud Faye, Lila Sainero, Alice Breton, et al.. Measuring Vagueness-Based Persuasion Techniques in an AI-Generated Influence Campaign. Journées Infox sur Seine 2026, François Bancilhon; Oana Balalau, Feb 2026, Paris, France. ⟨hal-05531214⟩

Florent Meyer, Laurent Guichard, Yann Soullard, Denis Coquenet, Guillaume Gravier, et al.. N-gram Injection into Transformers for Dynamic Language Model Adaptation in Handwritten Text Recognition. 2026. ⟨hal-05537580⟩