NL4AI 2026
Natural Language for Artificial Intelligence

Table of Contents

• Preface
  Summary: There were 26 papers submitted to this workshop, of which 3 were withdrawn. 14 long papers were accepted for this volume.
• NL4AI 2026: Overview of the Ninth Workshop on Natural Language for Artificial Intelligence (NL4AI 2026)
  Alessandro Bondielli, Giovanni Bonetta, Elisa Leonardelli, Irene Siragusa

Invited Talks

• Beyond Models: The Impact of AI on NLP through the Lens of Machine Translation
  Marco Turchi
• Back to the Future: From Models Back to Systems in NLP
  Lorenzo De Mattei

Long Papers

• Evaluating Clinical Coding Alignment Across ICD-9, ICD-10, and ICD-11 with a Semantic Retrieval Approach (short paper)
  Irene Siragusa, Roberto Pirrone
• Comparing Generated Pseudo-Labeled News Datasets: A Retrieval-and-Verification Approach
  Giulio Alfarano, Stefano Scotta, Alberto Messina
• Who Judges the Judges? A Multilingual Probe for Complementary LLM Evaluation Metrics
  Salvatore Ricciardi, Simone Scaboro, Beatrice Turano, Cristina Giannone, Andrea Favalli, Raniero Romagnoli
• Machine Translation of Low-Resource Historical Languages: A Comparative Study of LLMs on Old Occitan
  Francesco Colace, Sabrina Galano, Angelo Lorusso, Domenico Santaniello, Giusy Strollo, Annapia Tanzola
• Right for the Right Reasons? A Chain-of-Thought Analysis of Commonsense Causal Reasoning
  Serena Auriemma, Martina Miliani, Alessandro Bondielli, Lucia Passaro, Alessandro Lenci
• Evaluating Watermark Resilience in Italian Large Language Models Under Back-Translation Attacks
  Elena Opreni, Alice Pietrasanta, Davide Altieri, Giulia Rizzi, Elisabetta Fersini
• MAWGE: A Parametric and Synthetic Multi-Agentic Workflow Generator Library
  Goshgar C. Ismayilov
• Exploring the Relationship between Sparse Autoencoder Activations and Sentence Complexity (short paper)
  Ejdis Gjinika, Luca Putelli, Ivan Serina, Alfonso Emilio Gerevini
• The Prosody of Clinical Speech: Annotation and Computational Analysis of Psychiatric Interviews
  Claire Lawand, Haeeul Hwang, Jalal Al-Tamimi, Motasem Alrahabi, Mahshid Hozhabr, Deok-Hee Kim-Dufor, Christophe Lemey, Julien Desclés, Valeria Lucarini
• Static or Dynamic? Exploring Cross-Lingual Few-Shot Transfer for Indonesian Misogynistic Meme Detection
  Endang Wahyu Pamungkas, Maryam, Rona Rizkhy Bunga Chasana, Dade Nurjanah, Ikhlasul Amal
• Same Job, Different Gender: Uncovering LLM Stereotypes via Counterfactual Biographies
  Chiara Manno, Martina Miliani
• Scale or Specialization? Evaluating Language Models for Italian Fact Verification (short paper)
  Alessandro Pucci, Danilo Croce, Roberto Basili
• Does Perspective Matter? Annotation Role Alignment in Emotion Recognition (short paper)
  Samuele D’Avenia, Timothy Meinert, Marta Marchiori Manerba, Valerio Basile, Anna Koufakou
• Election-Based Evaluation Methods for NLG-Systems
  Michał Tomasz Godziszewski, Mateusz Galiński, Rzyszard Tuora, Mateusz Czyżnikiewicz, Tomasz Ziętkiewicz, Adam Kozakiewicz, Cristina Cornelio