Program

09.00 - 9.15

Opening: Paolo Traverso and Luisa Bentivogli

9.15 - 10.00

Keynote talk: Marco Turchi - Head of the Machine Translation group at Zoom

Beyond Models: The Impact of AI on NLP through the Lens of Machine Translation

Artificial intelligence is transforming how machines understand and generate human language. From chatbots to real-time transcription, large language models now handle translation, summarization, and speech recognition within a single framework — reshaping industries and redefining how people communicate across borders.

In this presentation, I use machine translation to cut through the hype and examine what this transformation actually looks like — both technically and organizationally. On the technology one, I trace how translation evolved from dedicated neural systems to general-purpose AI models, how quality is measured, and how text and speech translation are converging into real-time voice-to-voice pipelines. On the organizational side, I examine how these shifts are reshaping teams, demanding new competencies, and blurring the boundaries between translation, speech, and AI specialists. Drawing on practical experience deploying AI-based translation at scale at Zoom, the talk offers a candid look at where the technology delivers, where it falls short, and what it means for the teams building the next generation of multilingual AI.

10:00 - 10.30

Coffee break

10.30 - 12:00

Oral Session 1: Understanding, Benchmarking and Improving Language and Multimodal Models

1. Sara Papi, Marco Gaido, Danni Liu, Beatrice Savoldi, Maike Zufle, Luisa Bentivogli, Ioannis Douros, Jan Niehues: MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks. ICLR 2026.

2. Davide Testa, Hugh Mee Wong, Alessandro Lenci, Bernardo Magnini, Albert Gatt: From Vision to Language: Investigating Causal Information Flow in Multimodal Decision-Making. Findings of EMNLP 2026

3. Seraphina Fong, Marco Mattassoni, Alessio Brutti: Towards Enabling Multilingual Multitask SpeechLLMs in Data-Scarce Settings. Interspeech 2026.

4. Pietro Ferrazzi, Matteo Merler, Giovanni Bonetta, Alberto Lavelli, Bernardo Magnini: DECSELFMASK: Leveraging Unlabeled Text via Self-Relevance-Guided Masking for Decoder-Only Classification. EMNLP 2026.

5. Siaovsh Sepanta, Marco Mattassoni, Alessio Brutti: Privacy Leakage in Speech-LLMs: Detection and Mitigation. Interspeech 2026.

6. Leonardo Sanna, Erica Solinas, Mauro Dragoni: LLM-as-a-Judge for Evaluating the Quality of Retrieval-Augmented Generation Systems. AIME 2026.

12.00 - 13:00

Poster and Demo Session 1

Posters

1. Gianluca Apriceno, Tania Bailoni, Mauro Dragoni: Evaluating Temporal Clinical Reasoning and Audience-Tailored Explanations in Large Language Models

2. Giovanni Bonetta, Matteo Merler, Davide Zago, Rossella Cancelliere, Bernardo Magnini: Selective Agent Guidance via Entropy: Learning Autonomous Policies from Imperfect VLM Teachers. Findings of EMNLP

3. Helena Bonaldi, Genoveffa Martone, Marco Guerini: CATCH-ME if you RAG: a dataset of Contextually Annotated multi-Turn Counterspeech against Hate and Misinformation Exchanges. Arxiv

4. Monica Consolandi, Simone Magnolini, Mauro Dragoni: Risk Communication in Healthcare: The Management of Misunderstandings. J. Medical Syst.

5. Lina Conti, Dennis Fucci, Marco Gaido, Matteo Negri, Guillaume Wisniewski, Luisa Bentivogli: Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translation. LREC 2026

6. Pietro Ferrazzi, Aitor Soroa, Rodrigo Agerri: Multilingual Medical Reasoning for Question Answering with Large Language Models. Findings of EMNLP 2026

7. Giacomo Gonella, Stefano Menini, Marco Guerini: CrisiLangs: A Multilingual Resource for Crisis Warning Generation. Workshop Language Technologies for Crisis Preparedness and Response (LT4CPR)

8. Elisa Leonardelli, Camilla Casula, Boglarka Nyul and Sara Tonelli: Real Men are Tough: Evaluating Sensitivity and Gender Bias to Masculinity Norms in LLMs. Findings of ACL 2026

9. Mohammed Nabih, Daniele Falavigna, Alessio Brutti: Fed-SpeechLLM: Federated Learning Speech Language Models for Multilingual ASR. Interspeech 2026

10. Dhairya Suman, Marco Gaido, Matteo Negri: Escaping the Holistic Trap: Probing Linguistic Phenomena in Quantized LLMs for Machine Translation. AI*IA 2026.

11.Davide Testa, Gloria Comandini, Manuela Speranza, Sofia Brenna, Stefania Cavagnoli and B Magnini: What is my Age (and Gender) again? Profiling AI Systems Through the Lens of Gender Stereotype Detection, Clic-it 2026 / LREC

12. Sebastiano Vecellio Salto, Camilla Casula, Alessio Palmero Aprosio and Sara Tonelli: University Speaking for Everyone: Assessing Changes in Italian Higher Education Statutes Toward Gender-Inclusive Language. LREC 2026

Demos

1. Lorenzo Concina, Marco Matassoni, Alessio Brutti, SpeakeRAGent: A Voice-Anchored Memory Layer for conversational agents

2. Marco Gaido, Sara Papi, Mauro Cettolo, Matteo Negri, Luisa Bentivogli: Simulstream: Open-Source Toolkit for Evaluation and Demonstration of Streaming Speech-to-Text Translation Systems. EMNLP 2026 Demo.

3. Leonardo Bottona, Nicolò Penzo, Bruno Lepri, Marco Guerini, Sara Tonelli: LLMberjack: Guided Trimming of Debate Trees for Multi-Party Conversation Creation. EMNLP 2026 demo

4. Leonardo Sanna, Mattia Franzin, Mauro Dragoni, Claudio Eccher: Flow Builder: No-Code Conversation Design Tool for Digital Therapeutics in Psychology.

13.00 - 14.00

Lunch

14.00 - 14.45

Keynote talk: Antonella De Angeli - Free University of Bozen-Bolzano

Title: tba

14.45 - 16:15

Oral Session 2: Human-Centred LT: Evaluation, Interaction and Social Applications

1. Giuseppe Attanasio, Beatrice Savoldi, Daniel Chechelnitsky, Marine Carpuat, Matteo Negri, Marteen Sap, Andre Martins: Ouvia: A User-Centered Benchmark for Usability Assessment of Speech Translation Systems. EMNLP 2026

2. Daniel Russo, Marco Antonio Stranisci, Oscar Araque, Marco Guerini: MoralTrajectories: Evaluating Moral Steerability in Large Language Models. Findings of EMNLP 2026

3. Marco Rovera, Sergiu Burlacu, Dominique Cappelletti, Alessio Tomelleri, Sonia Marzadro, Martina Bazzoli, Annalisa Tassi, Jessica Gagete-Miranda: Research Design Tracking and Assessment for the Social Sciences. EMNLP 2026.

4. Daniela Occhipinti, Malvina Nissim, Marco Guerini: Stranger, Fan, or Peer? A Systematic Study on The Role of Interlocutor in Persona-Based Dialogue Generation. EMNLP 2026

5. Giovanni Valer, Elisa Leonardelli, Camilla Casula, Sara Tonelli, Michele Lombardi: Annotators of a Feather FLOCKE Together: A Framework to Analyze Latent Group Patterns Based on Annotator Behavior. EMNLP 2026.

6. Saba Ghanbari Haez, Claudio Giuliano, Renan Lirio de Souza, Mauro Dragoni: How Do LLMs Handle Conflict in Healthcare? Hierarchy, Collaboration Defaults, and Autonomy. AIME 2026

16.15 - 16.30

Highlight talk: Giulia Olivato - legal researcher at the Ethics and Legal Innovation Lab at Fondazione Bruno Kessler

Title: tba

16.30 - 17.20

Poster and Demo Session 2 + Coffee break

External Posters

The session will feature posters from Eurac Research, Free University of Bozen-Bolzano, University of Padua, University of Trento, Almawave, and GESIS.

Poster titles and details will be announced soon.

Demos

1. Veronica Orsanigo, Riccardo Marcuzzi, Elisa Leonardelli, Nicolò Penzo, Riccardo Gallotti, Marco Guerini, Sara Tonelli: Research Intelligence Tool. FBK Internal project

2. Mauro Cettolo*, Elia Soliman*, Roldano Cattoni, Matteo Negri, Luisa Bentivogli, Alessio Palmero Aprosio: SENSEI: A Simple, Elegant, and Nimble Subtitle Editing Interface. Clic-it 2026.

3. Piergiorgio Maruotti, Mattia Rampazzo, Sergio Muñoz, Mauro Dragoni, Patrizio Bellan: Assessing Mental Health Therapeutic Capacity in AI Agents. AIME 2026

4. Marco Rovera: PolicyAid Platform

17.20 - 17.30

Closing remarks

Page updated

Report abuse