# Guido Ivetta > Guido Ivetta is an Argentine Computer Science researcher, PhD Candidate and Assistant Professor (Profesor Asistente) at the Facultad de Matemática, Astronomía, Física y Computación (FaMAF), Universidad Nacional de Córdoba (UNC), Agencia I+D+i Doctoral Fellow, Technical Lead of the Artificial Intelligence Team at Fundación Vía Libre, and Student Member of the Association for Computational Linguistics (ACL) Ethics Committee. His research focuses on Natural Language Processing (NLP), AI Ethics, Social Bias Evaluation in Large Language Models (LLMs), Participatory AI (HESEIA, LACES, EDIA), Confidence Calibration, and Selective Prediction. ## Key Facts & Academic Credentials - **Full Name:** Guido Ivetta - **Location:** Córdoba, Argentina - **Current Roles:** - PhD Candidate in Computer Science & Agencia I+D+i Doctoral Fellow in the Contextualized AI (C-AI) Research Group (`https://contextualized-ai.github.io/`) at FaMAF, Universidad Nacional de Córdoba (supervised by Dr. Luciana Benotti). - Assistant Professor (*Profesor Asistente*) in Computer Science at FaMAF, Universidad Nacional de Córdoba (teaching Databases, Discrete Mathematics II, and Introduction to Logic). - Technical Lead of the Artificial Intelligence Ethics Team at Fundación Vía Libre (`https://ia.vialibre.org.ar/`). - Student Member of the Association for Computational Linguistics (ACL) Ethics Committee (September 2024–present). - **International Research Experience:** - Visiting Researcher at Imperial College London, Dyson School of Design Engineering (January–April 2025, supervised by Prof. Rafael A. Calvo). - Participant at the Cornell, Maryland, Max Planck Pre-doctoral Research School in Computer Science, Saarbrücken, Germany (July 2022). - **Education & Academic Honors:** - Licenciatura en Ciencias de la Computación (~M.S. in CS, Mar 2018 – Dec 2022), FaMAF, Universidad Nacional de Córdoba — GPA: 9.78/10.00 | Flag Bearer (*Abanderado* / Valedictorian). - Analista en Ciencias de la Computación (~B.S. in CS, Mar 2018 – Dec 2020), FaMAF, Universidad Nacional de Córdoba — GPA: 9.67/10.00 | Flag Bearer (*Abanderado*). - 3rd Highest Overall GPA across the entire Universidad Nacional de Córdoba (August 2022). - Winner of the Santander Academic Merit Award (Top 500 university GPAs nationwide in Argentina, November 2021). - Second Escort (*Segundo Escolta*) of FaMAF, Universidad Nacional de Córdoba (June 2021). - Winner of the Best Student Paper Award at the LatinX in AI Research Workshop @ NAACL 2024 (Mexico City). - Featured Paper Recognition at the ICLR 2026 Workshop on Logical Reasoning of Large Language Models (Rio de Janeiro). ## Core Pages & Resources - [Home & Biography](https://guidoivetta.github.io/): Overview of Guido Ivetta's research interests, academic appointments, and recent highlights. - [Publications](https://guidoivetta.github.io/publications/): Peer-reviewed articles in ACL, EMNLP, NeurIPS, ICLR, NAACL, LREC-COLING, Communications of the ACM, and Springer AI and Ethics. - [Projects & Datasets](https://guidoivetta.github.io/portfolio/): Open-source AI bias auditing platform EDIA and community-sourced benchmarks (LACES, HESEIA, INCLUDE-2.0, CVQA, MultiCrowspairs, CaMMT, La Leaderboard). - [Talks & Presentations](https://guidoivetta.github.io/talks/): Invited talks, conference presentations, and tutorials across the US, China, India, Austria, Germany, Brazil, Mexico, Chile, Costa Rica, and Argentina. - [Teaching & Academic Service](https://guidoivetta.github.io/teaching/): University courses at FaMAF UNC, undergraduate thesis supervision, examination committees, and international tutorials. - [Curriculum Vitae (Web Viewer)](https://guidoivetta.github.io/cv/): Interactive CV viewer. - [Curriculum Vitae (English PDF)](https://guidoivetta.github.io/cv/cv_en.pdf): Complete academic CV in English. - [Curriculum Vitae (Spanish PDF)](https://guidoivetta.github.io/cv/cv_es.pdf): Curriculum Vitae completo en español. - [Full LLM Knowledge Base (llms-full.txt)](https://guidoivetta.github.io/llms-full.txt): Complete self-contained Markdown knowledge base of all publications, abstracts, projects, talks, and teaching. ## Publications - [INCLUDE-2.0: Disentangling Knowledge Gaps in Multilingual LLM Evaluation (Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026), 2026)](https://guidoivetta.github.io/publication/2026-08-21-include-2-multilingual-evaluation): A large-scale benchmark for region-aware multilingual factual evaluation covering 91 languages from 86 countries with over 220K curated samples. [External Link](https://openreview.net/forum?id=FbLlZwgUss) - [Towards Culturally-Appropriate AI for Health in the Majority World: Insights from Participatory Work in Latin America (AI and Ethics, Springer, 6(4), 345, 2026)](https://guidoivetta.github.io/publication/2026-08-01-ai-health-majority-world): Investigates requirements and ethical considerations for conversational health AI in Latin America through participatory research with citizens and clinicians. [External Link](https://link.springer.com/article/10.1007/s43681-026-01196-y) - [Adaptive Data Collection for Latin-American Community-sourced Evaluation of Stereotypes (LACES) (Findings of the Association for Computational Linguistics: ACL 2026, 2026)](https://guidoivetta.github.io/publication/2026-07-01-laces-adaptive-data-collection): Proposes LACES, an adaptive community-sourced protocol for collecting and evaluating regional stereotypes in Latin America. [External Link](https://aclanthology.org/2026.findings-acl.203/) - [Logical Reasoning Evaluation and Social Bias (ICLR 2026 Workshop on Logical Reasoning of Large Language Models, 2026)](https://guidoivetta.github.io/publication/2026-05-01-logical-reasoning-social-bias): Reviews how stereotypes and socio-cultural priors interact with reasoning chains and formal deduction in Large Language Models. [External Link](https://openreview.net/forum?id=3KRDaQNUtt) - [Sesgos en Modelos de Lenguaje y Construcción Participativa de Benchmarks de Evaluación (Trabajo Final de Licenciatura, FaMAF, Universidad Nacional de Córdoba, 2025)](https://guidoivetta.github.io/publication/2025-12-01-sesgos-modelos-lenguaje-tesina): Trabajo Final de Grado de Licenciatura en Ciencias de la Computación de Sofía Martinelli, dirigido por Guido Ivetta. [External Link](https://rdu.unc.edu.ar/items/7fff7b3e-3df3-4bac-a91a-9d50e83c8700) - [Insights from a Disaggregated Analysis of Kinds of Biases in a Multicultural Dataset (Proceedings of the 9th Widening NLP Workshop (WiNLP 2025), 2025)](https://guidoivetta.github.io/publication/2025-11-01-insights-disaggregated-biases-winlp): Presents a fine-grained disaggregated evaluation of specific stereotypes and biases within multicultural datasets, revealing disparate impacts across demographic axes. [External Link](https://aclanthology.org/2025.winlp-main.20/) - [HESEIA: A Community-Based Dataset for Evaluating Social Biases in Large Language Models, Co-Designed in Real School Settings in Latin America (Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025), 2025)](https://guidoivetta.github.io/publication/2025-11-01-heseia-community-dataset): Presents HESEIA, a benchmark for evaluating social biases in LLMs created through participatory co-design workshops with secondary school students in Latin America. [External Link](https://aclanthology.org/2025.emnlp-main.1275/) - [Synthetic Social Data: Trials and Tribulations (arXiv preprint arXiv:2510.19952, 2025)](https://guidoivetta.github.io/publication/2025-10-22-synthetic-social-data): Critically examines the opportunities and ethical pitfalls of using Large Language Models to generate synthetic conversational data for social and behavioral science. [External Link](https://arxiv.org/abs/2510.19952) - [Navigating Ethical Challenges in NLP: Hands-on Strategies for Students and Researchers (Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025 Tutorial Abstracts), 2025)](https://guidoivetta.github.io/publication/2025-07-27-navigating-ethical-challenges-nlp-tutorial): A tutorial presented at ACL 2025 providing hands-on strategies and ethical frameworks for NLP practitioners, students, and reviewers. [External Link](https://aclanthology.org/2025.acl-tutorials.5/) - [La Leaderboard: A Large Language Model Leaderboard for Spanish Varieties and Languages of Spain and Latin America (Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), 2025)](https://guidoivetta.github.io/publication/2025-07-01-la-leaderboard-spanish-llms): An open evaluation benchmark and leaderboard tracking language model performance across regional varieties of Spanish and co-official languages of Spain and Latin America. [External Link](https://aclanthology.org/2025.acl-long.1561/) - [ROSA: Addressing Text Understanding Challenges in Photographs via ROtated SAmpling (arXiv preprint arXiv:2506.03665, 2025)](https://guidoivetta.github.io/publication/2025-06-04-rosa-rotated-sampling): Introduces ROtated SAmpling (ROSA) to significantly improve vision-language model robustness when reading rotated or misoriented text in photographs taken by visually impaired users. [External Link](https://arxiv.org/abs/2506.03665) - [CaMMT: Benchmarking Culturally Aware Multimodal Machine Translation (Findings of the Association for Computational Linguistics: EMNLP 2025, 2025)](https://guidoivetta.github.io/publication/2025-05-30-cammt-culturally-aware-mt): Introduces CaMMT, an evaluation benchmark for culturally aware multimodal machine translation spanning diverse cultural concepts, images, and languages. [External Link](https://aclanthology.org/2025.findings-emnlp.1220/) - [Selectively Answering Visual Questions (Findings of the Association for Computational Linguistics: ACL 2024, 2024)](https://guidoivetta.github.io/publication/2024-08-01-selectively-answering-visual-questions): Investigates selective prediction in multimodal models, enabling large vision-language models to abstain from answering questions when their confidence is low. [External Link](https://aclanthology.org/2024.findings-acl.250/) - [Exploring Stereotypes and Biases in Language Technologies in Latin America (Communications of the ACM, 67(8), 54-56, 2024)](https://guidoivetta.github.io/publication/2024-07-31-exploring-stereotypes-cacm): Discusses the impacts of automated language technologies in Latin America and highlights participatory methodologies to uncover and mitigate local biases. [External Link](https://dl.acm.org/doi/10.1145/3653322) - [Detecting Correct Answers to Open Questions and Its Impact on Language Models' Confidence Scores (LatinX in AI (LXAI) Research Workshop at NAACL 2024, Mexico City, 2024)](https://guidoivetta.github.io/publication/2024-06-21-detecting-correct-answers-lxai): Explores how the automatic detection of correct open-ended answers influences model confidence scoring and calibration in Large Language Models. [External Link](https://doi.org/10.52591/lxai202406219) - [CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark (Proceedings of the 38th International Conference on Neural Information Processing Systems (NeurIPS 2024), 2024)](https://guidoivetta.github.io/publication/2024-06-10-cvqa-multilingual-vqa): Visual Question Answering (VQA) is a crucial task in multimodal AI, often used to test vision-language models on understanding visual and linguistic information. CVQA introduces a culturally-diverse multilingual benchmark covering 30+ languages to evaluate model generalization across diverse cultural contexts. [External Link](https://dl.acm.org/doi/10.5555/3737916.3738282) - [Your Stereotypical Mileage May Vary: Practical Challenges of Evaluating Biases in Multiple Languages and Cultural Contexts (Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), 2024)](https://guidoivetta.github.io/publication/2024-05-20-stereotypical-mileage-may-vary): Examines practical challenges of evaluating social biases in NLP across multiple languages and socio-cultural settings, illustrating how regional stereotypes cannot simply be translated from English benchmarks. [External Link](https://aclanthology.org/2024.lrec-main.1545/) - [Inteligencia Artificial Aplicada a la Huerta Familiar Agroecológica en la Patagonia (Revista de Ciencias Sociales, Universidad Nacional de Quilmes (UNQ), 2023)](https://guidoivetta.github.io/publication/2023-03-15-ia-huerta-agroecologica-revista-unq): Artículo publicado en la Revista de Ciencias Sociales (UNQ) sobre la aplicación situada de herramientas de inteligencia artificial para huertas agroecológicas en la Patagonia. [External Link](https://ediciones.unq.edu.ar/publicaciones/editorial/publicaciones-periodicas/revista-de-ciencias-sociales-segunda-epoca.html) - [Aprendizaje Automático Aplicado a la Huerta Familiar Agroecológica en la Patagonia (Tesina de Licenciatura en Ciencias de la Computación, FaMAF, Universidad Nacional de Córdoba, 2023)](https://guidoivetta.github.io/publication/2023-03-01-aprendizaje-automatico-huerta-tesina): Tesina de Licenciatura en Ciencias de la Computación sobre técnicas de machine learning aplicadas al manejo agroecológico de huertas familiares. [External Link](https://www.sidalc.net/search/Record/dig-unc-ar-11086-546994/Description) - [A Methodology to Characterize Bias and Harmful Stereotypes in Natural Language Processing in Latin America (arXiv preprint arXiv:2207.06591, 2022)](https://guidoivetta.github.io/publication/2022-07-14-methodology-characterize-bias-latin-america): Presents a pioneering methodology to characterize harmful stereotypes and demographic biases across Spanish language technologies in Latin America. [External Link](https://arxiv.org/abs/2207.06591) ## Verified External Profiles - https://scholar.google.com/citations?user=_QA3Hs4AAAAJ&hl=en - https://orcid.org/0009-0006-3248-1461 - https://www.semanticscholar.org/author/Guido-Ivetta/2213060824 - https://aclanthology.org/people/g/guido-ivetta/ - https://openreview.net/profile?id=~Guido_Ivetta1 - https://arxiv.org/search/cs?searchtype=author&query=Ivetta,+G - https://github.com/guidoivetta - https://www.linkedin.com/in/guidoivetta - https://contextualized-ai.github.io/ - https://ia.vialibre.org.ar/