# Guido Ivetta — Full Academic Knowledge Base (llms-full.txt) > Comprehensive, authoritative reference document for AI search engines, retrieval-augmented generation (RAG) systems, and large language models summarizing the biography, academic credentials, honors, research projects, publications, invited talks, and university teaching of Guido Ivetta (`https://guidoivetta.github.io/`). --- ## 1. Executive Summary (English & Español) **English:** **Guido Ivetta** is an Argentine Computer Science researcher, PhD Candidate in Computer Science and **Agencia I+D+i Doctoral Fellow** in the **Contextualized AI (C-AI) Research Group** (`https://contextualized-ai.github.io/`) at the **Facultad de Matemática, Astronomía, Física y Computación (FaMAF), Universidad Nacional de Córdoba (UNC)**, supervised by Dr. Luciana Benotti. He graduated as **Abanderado (Flag Bearer / Valedictorian)** of FaMAF with a GPA of **9.78/10.00**—the **3rd highest GPA across the entire Universidad Nacional de Córdoba**—and serves as an **Assistant Professor (*Profesor Asistente*)** in Computer Science at FaMAF UNC. Alongside his academic appointments, he is the **Technical Lead of the Artificial Intelligence Team at Fundación Vía Libre** (a leading Argentine civil rights NGO), a **Student Member of the Association for Computational Linguistics (ACL) Ethics Committee**, and was a Visiting Researcher at **Imperial College London** (January–April 2025, supervised by Prof. Rafael A. Calvo). **Español:** **Guido Ivetta** es investigador en Ciencias de la Computación, doctorando en Ciencias de la Computación con **Beca Doctoral de la Agencia I+D+i** en el grupo **C-AI — Inteligencia Artificial Contextualizada** (`https://contextualized-ai.github.io/`) y **Profesor Asistente** en la **Facultad de Matemática, Astronomía, Física y Computación (FaMAF)** de la **Universidad Nacional de Córdoba (UNC)**, dirigido por la Dra. Luciana Benotti. Egresó como **Abanderado de la FAMAF** con el mejor promedio de su promoción (**9.78/10.00**) y el **3.er Mejor Promedio General de toda la Universidad Nacional de Córdoba**. Es **Líder Técnico del Equipo de Inteligencia Artificial en la Fundación Vía Libre**, **Miembro Estudiantil del Comité de Ética de la Association for Computational Linguistics (ACL)** y realizó una estancia de investigación en el **Imperial College London** (Reino Unido, enero–abril de 2025, supervisado por el Prof. Rafael A. Calvo). --- ## 2. Education & Academic Distinctions - **PhD in Computer Science (Doctorado en Ciencias de la Computación)** — *FaMAF, Universidad Nacional de Córdoba* (2023 – Present). - Dissertation Topic: *Natural Language Processing, Confidence Calibration, Selective Prediction, and Participatory Bias Evaluation in Large Language Models*. - Advisor: Dr. Luciana Benotti. - **Visiting Researcher** — *Dyson School of Design Engineering, Imperial College London, United Kingdom* (January 2025 – April 2025). - Supervisor: Prof. Rafael A. Calvo. Research on synthetic social data, healthcare AI in the majority world, and participatory evaluation. - **Licenciatura en Ciencias de la Computación (~M.S. in CS)** — *FaMAF, Universidad Nacional de Córdoba* (March 2018 – December 2022). - GPA: **9.78 / 10.00** | *Abanderado* (~Valedictorian). - Thesis: *"Aprendizaje Automático Aplicado a la Huerta Familiar Agroecológica en la Patagonia"* (Advisor: Dr. Luciana Benotti). - **Analista en Ciencias de la Computación (~B.S. in CS)** — *FaMAF, Universidad Nacional de Córdoba* (March 2018 – December 2020). - GPA: **9.67 / 10.00** | *Abanderado* (~Valedictorian). - **Pre-Doctoral Research School** — *Cornell, Maryland, Max Planck Pre-doctoral Research School in Computer Science*, Max Planck Institute for Software Systems (MPI-SWS), Saarbrücken, Germany (July 2022). ### Honors, Awards & Fellowships 1. **Featured Paper Recognition — ICLR 2026 Workshop on Logical Reasoning of Large Language Models** (Rio de Janeiro, Brazil, April 2026) for *"Logical Reasoning Evaluation and Social Bias"*. 2. **Best Student Paper Award — LatinX in AI Research Workshop at NAACL 2024** (Mexico City, Mexico, June 2024) for *"Detecting Correct Answers to Open Questions and Its Impact on Language Models' Confidence Scores"*. 3. **Agencia I+D+i Doctoral Fellowship** (November 2023 – November 2026). 4. **3rd Highest Overall GPA across the entire Universidad Nacional de Córdoba** (August 2022). 5. **Flag Bearer (*Abanderado*) of FaMAF, Universidad Nacional de Córdoba** (May 2022), awarded for the highest GPA in the 5th year at FaMAF (9.78/10). 6. **Santander Academic Merit Award (*Premio al Mérito Académico Banco Santander*)** (November 2021), awarded to the top 500 university GPAs nationwide in Argentina. 7. **Second Escort (*Segundo Escolta*) of FaMAF, Universidad Nacional de Córdoba** (June 2021), awarded for the highest GPA in the 4th year at FaMAF. --- ## 3. Research Projects, Open-Source Platforms & Benchmarks 1. **EDIA & EDIA 2.0 Multimodal (Fundación Vía Libre)** - URL: `https://ia.vialibre.org.ar/edia1-0/` | `https://ia.vialibre.org.ar/ediamultimodal2-0/` - Role: Technical Lead & Core Architect. - Description: An open-source graphical auditing toolkit enabling domain experts, sociologists, journalists, and educators (without programming backgrounds) to detect, measure, and visualize stereotypes and discrimination in word embeddings, large language models, and multimodal image generation models. Featured in *Communications of the ACM* (2024), demonstrated via hands-on tutorial at *ACM FAccT 2024* (Rio de Janeiro), and presented at *RightsCon 2023* (Costa Rica). 2. **HESEIA: Community-Based Social Bias Benchmark in Secondary Schools** - URL: `https://aclanthology.org/2025.emnlp-main.1275/` - Role: First Author & Technical Lead. - Description: A large-scale participatory dataset of **46,499 diagnostic sentences** co-designed in real classrooms across Argentina with **370 teachers and over 5,000 secondary school students across 189 schools** to evaluate social biases in LLMs while fostering critical AI literacy. Presented orally in the main track of *EMNLP 2025* (Suzhou, China) and showcased at the *India AI Impact Summit 2026* (New Delhi, India). 3. **LACES: Adaptive Data Collection for Latin-American Community-Sourced Evaluation of Stereotypes** - URL: `https://aclanthology.org/2026.findings-acl.203/` | `https://arxiv.org/abs/2510.24958` - Role: First Author & Lead Researcher. - Description: An adaptive, iterative community-sourced protocol that overcomes static translation limitations to capture and validate regional stereotypes across Latin American varieties of Spanish. Published in *Findings of ACL 2026* (San Diego, USA). 4. **INCLUDE-2.0: Region-Aware Multilingual LLM Evaluation** - URL: `https://openreview.net/forum?id=FbLlZwgUss` | `https://huggingface.co/datasets/epfl-nlp/include-2.0` - Role: Co-author (Argentine / Latin American regional benchmark lead). - Description: A massive multilingual benchmark spanning **91 languages across 86 countries (127 language–country pairs)** and **220,000+ samples** from authentic local examinations, disentangling language fluency from regional cultural and institutional knowledge. Published in *EMNLP 2026 Main Conference*. 5. **CVQA: Culturally-Diverse Multilingual Visual Question Answering** - URL: `https://cvqa-benchmark.org/` | `https://arxiv.org/abs/2406.05967` - Role: Co-author (Argentina cultural & linguistic contributor). - Description: A culturally grounded VQA benchmark spanning 30+ languages and diverse regions worldwide, published at *NeurIPS 2024*. 6. **La Leaderboard & CaMMT & MultiCrowspairs** - *La Leaderboard* (*ACL 2025*): Evaluation suite for Spanish dialectal varieties and co-official languages in Latin America and Spain (`https://aclanthology.org/2025.acl-long.1561/`). - *CaMMT* (*Findings of EMNLP 2025*): Culturally Aware Multimodal Machine Translation benchmark (`https://aclanthology.org/2025.findings-emnlp.1220/`). - *MultiCrowspairs* (*LREC-COLING 2024*): Cross-cultural stereotype benchmark analysis (`https://aclanthology.org/2024.lrec-main.1545/`). --- ## 4. Complete Catalog of Publications ### 1. INCLUDE-2.0: Disentangling Knowledge Gaps in Multilingual LLM Evaluation (2026) - **Venue:** Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026) - **Citation:** Angelika Romanou, María Grandury, Clara Meister, Negar Foroutan, ..., Guido Ivetta, et al. (2026). "INCLUDE-2.0: Disentangling Knowledge Gaps in Multilingual LLM Evaluation." EMNLP 2026. - **Summary:** A large-scale benchmark for region-aware multilingual factual evaluation covering 91 languages from 86 countries with over 220K curated samples. - **URL:** `https://guidoivetta.github.io/publication/2026-08-21-include-2-multilingual-evaluation` | **External Paper Link:** `https://openreview.net/forum?id=FbLlZwgUss` ### 2. Towards Culturally-Appropriate AI for Health in the Majority World: Insights from Participatory Work in Latin America (2026) - **Venue:** AI and Ethics, Springer, 6(4), 345 - **Citation:** Dorian Peters, Fernanda Espinoza, Marco da Re, Guido Ivetta, Luciana Benotti, Rafael A. Calvo. (2026). "Towards Culturally-Appropriate AI for Health in the Majority World: Insights from Participatory Work in Latin America." AI and Ethics, 6(4), 345. - **Summary:** Investigates requirements and ethical considerations for conversational health AI in Latin America through participatory research with citizens and clinicians. - **URL:** `https://guidoivetta.github.io/publication/2026-08-01-ai-health-majority-world` | **External Paper Link:** `https://link.springer.com/article/10.1007/s43681-026-01196-y` ### 3. Adaptive Data Collection for Latin-American Community-sourced Evaluation of Stereotypes (LACES) (2026) - **Venue:** Findings of the Association for Computational Linguistics: ACL 2026 - **Citation:** Guido Ivetta, Pietro Palombini, Sofía Martinelli, Marcos J. Gomez, M. Emilia Echeveste, Sunipa Dev, Vinodkumar Prabhakaran, Luciana Benotti. (2026). "Adaptive Data Collection for Latin-American Community-sourced Evaluation of Stereotypes (LACES)." Findings of ACL 2026, pp. 4177–4190. - **Summary:** Proposes LACES, an adaptive community-sourced protocol for collecting and evaluating regional stereotypes in Latin America. - **URL:** `https://guidoivetta.github.io/publication/2026-07-01-laces-adaptive-data-collection` | **External Paper Link:** `https://aclanthology.org/2026.findings-acl.203/` ### 4. Logical Reasoning Evaluation and Social Bias (2026) - **Venue:** ICLR 2026 Workshop on Logical Reasoning of Large Language Models - **Citation:** Sofia Martinelli, Guido Ivetta, Luciana Benotti. (2026). "Logical Reasoning Evaluation and Social Bias." ICLR 2026 Workshop on Logical Reasoning of Large Language Models. - **Summary:** Reviews how stereotypes and socio-cultural priors interact with reasoning chains and formal deduction in Large Language Models. - **URL:** `https://guidoivetta.github.io/publication/2026-05-01-logical-reasoning-social-bias` | **External Paper Link:** `https://openreview.net/forum?id=3KRDaQNUtt` ### 5. Sesgos en Modelos de Lenguaje y Construcción Participativa de Benchmarks de Evaluación (2025) - **Venue:** Trabajo Final de Licenciatura, FaMAF, Universidad Nacional de Córdoba - **Citation:** Sofía Martinelli (Dirigida por Guido Ivetta). (2025). "Sesgos en Modelos de Lenguaje y Construcción Participativa de Benchmarks de Evaluación." Trabajo Final de Grado, FaMAF, Universidad Nacional de Córdoba. - **Summary:** Trabajo Final de Grado de Licenciatura en Ciencias de la Computación de Sofía Martinelli, dirigido por Guido Ivetta. - **URL:** `https://guidoivetta.github.io/publication/2025-12-01-sesgos-modelos-lenguaje-tesina` | **External Paper Link:** `https://rdu.unc.edu.ar/items/7fff7b3e-3df3-4bac-a91a-9d50e83c8700` ### 6. Insights from a Disaggregated Analysis of Kinds of Biases in a Multicultural Dataset (2025) - **Venue:** Proceedings of the 9th Widening NLP Workshop (WiNLP 2025) - **Citation:** Guido Ivetta, Hernán Maina, Luciana Benotti. (2025). "Insights from a Disaggregated Analysis of Kinds of Biases in a Multicultural Dataset." Proceedings of the 9th Widening NLP Workshop, pp. 116–122. - **Summary:** Presents a fine-grained disaggregated evaluation of specific stereotypes and biases within multicultural datasets, revealing disparate impacts across demographic axes. - **URL:** `https://guidoivetta.github.io/publication/2025-11-01-insights-disaggregated-biases-winlp` | **External Paper Link:** `https://aclanthology.org/2025.winlp-main.20/` ### 7. HESEIA: A Community-Based Dataset for Evaluating Social Biases in Large Language Models, Co-Designed in Real School Settings in Latin America (2025) - **Venue:** Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025) - **Citation:** Guido Ivetta, Marcos J. Gomez, Sofía Martinelli, Pietro Palombini, M. Emilia Echeveste, Nair Carolina Mazzeo, Beatriz Busaniche, Luciana Benotti. (2025). "HESEIA: A Community-Based Dataset for Evaluating Social Biases in Large Language Models, Co-Designed in Real School Settings in Latin America." EMNLP 2025, pp. 25106–25128. - **Summary:** Presents HESEIA, a benchmark for evaluating social biases in LLMs created through participatory co-design workshops with secondary school students in Latin America. - **URL:** `https://guidoivetta.github.io/publication/2025-11-01-heseia-community-dataset` | **External Paper Link:** `https://aclanthology.org/2025.emnlp-main.1275/` ### 8. Synthetic Social Data: Trials and Tribulations (2025) - **Venue:** arXiv preprint arXiv:2510.19952 - **Citation:** Guido Ivetta, Laura Moradbakhti, Rafael A. Calvo. (2025). "Synthetic Social Data: Trials and Tribulations." arXiv:2510.19952. - **Summary:** Critically examines the opportunities and ethical pitfalls of using Large Language Models to generate synthetic conversational data for social and behavioral science. - **URL:** `https://guidoivetta.github.io/publication/2025-10-22-synthetic-social-data` | **External Paper Link:** `https://arxiv.org/abs/2510.19952` ### 9. Navigating Ethical Challenges in NLP: Hands-on Strategies for Students and Researchers (2025) - **Venue:** Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025 Tutorial Abstracts) - **Citation:** Luciana Benotti, Fanny Ducel, Karën Fort, Guido Ivetta, Zhijing Jin, Min-Yen Kan, Seung-Hun J. Lee, Minzhi Li, Margot Mieskes, Adriana Pagano. (2025). "Navigating Ethical Challenges in NLP: Hands-on Strategies for Students and Researchers." ACL 2025. - **Summary:** A tutorial presented at ACL 2025 providing hands-on strategies and ethical frameworks for NLP practitioners, students, and reviewers. - **URL:** `https://guidoivetta.github.io/publication/2025-07-27-navigating-ethical-challenges-nlp-tutorial` | **External Paper Link:** `https://aclanthology.org/2025.acl-tutorials.5/` ### 10. La Leaderboard: A Large Language Model Leaderboard for Spanish Varieties and Languages of Spain and Latin America (2025) - **Venue:** Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025) - **Citation:** María Grandury, Javier Aula-Blasco, Júlia Falcão, Clémentine Fourrier, ..., Guido Ivetta, ..., Irune Zubiaga. (2025). "La Leaderboard: A Large Language Model Leaderboard for Spanish Varieties and Languages of Spain and Latin America." ACL 2025, pp. 32482–32524. - **Summary:** An open evaluation benchmark and leaderboard tracking language model performance across regional varieties of Spanish and co-official languages of Spain and Latin America. - **URL:** `https://guidoivetta.github.io/publication/2025-07-01-la-leaderboard-spanish-llms` | **External Paper Link:** `https://aclanthology.org/2025.acl-long.1561/` ### 11. ROSA: Addressing Text Understanding Challenges in Photographs via ROtated SAmpling (2025) - **Venue:** arXiv preprint arXiv:2506.03665 - **Citation:** Hernán Maina, Guido Ivetta, Mateo Lione Stuto, Julian Martin Eisenschlos, Jorge Sánchez, Luciana Benotti. (2025). "ROSA: Addressing Text Understanding Challenges in Photographs via ROtated SAmpling." arXiv:2506.03665. - **Summary:** Introduces ROtated SAmpling (ROSA) to significantly improve vision-language model robustness when reading rotated or misoriented text in photographs taken by visually impaired users. - **URL:** `https://guidoivetta.github.io/publication/2025-06-04-rosa-rotated-sampling` | **External Paper Link:** `https://arxiv.org/abs/2506.03665` ### 12. CaMMT: Benchmarking Culturally Aware Multimodal Machine Translation (2025) - **Venue:** Findings of the Association for Computational Linguistics: EMNLP 2025 - **Citation:** Emilio Villa-Cueva, Sholpan Bolatzhanova, Diana Turmakhan, ..., Guido Ivetta, ..., Thamar Solorio. (2025). "CaMMT: Benchmarking Culturally Aware Multimodal Machine Translation." Findings of EMNLP 2025. - **Summary:** Introduces CaMMT, an evaluation benchmark for culturally aware multimodal machine translation spanning diverse cultural concepts, images, and languages. - **URL:** `https://guidoivetta.github.io/publication/2025-05-30-cammt-culturally-aware-mt` | **External Paper Link:** `https://aclanthology.org/2025.findings-emnlp.1220/` ### 13. Selectively Answering Visual Questions (2024) - **Venue:** Findings of the Association for Computational Linguistics: ACL 2024 - **Citation:** Julian Martin Eisenschlos, Hernán Maina, Guido Ivetta, Luciana Benotti. (2024). "Selectively Answering Visual Questions." Findings of the Association for Computational Linguistics: ACL 2024, pp. 4219–4229. - **Summary:** Investigates selective prediction in multimodal models, enabling large vision-language models to abstain from answering questions when their confidence is low. - **URL:** `https://guidoivetta.github.io/publication/2024-08-01-selectively-answering-visual-questions` | **External Paper Link:** `https://aclanthology.org/2024.findings-acl.250/` ### 14. Exploring Stereotypes and Biases in Language Technologies in Latin America (2024) - **Venue:** Communications of the ACM, 67(8), 54-56 - **Citation:** Hernán Maina, Laura Alonso Alemany, Guido Ivetta, Mariela Rajngewerc, Beatriz Busaniche, Luciana Benotti. (2024). "Exploring Stereotypes and Biases in Language Technologies in Latin America." Communications of the ACM, 67(8), 54-56. - **Summary:** Discusses the impacts of automated language technologies in Latin America and highlights participatory methodologies to uncover and mitigate local biases. - **URL:** `https://guidoivetta.github.io/publication/2024-07-31-exploring-stereotypes-cacm` | **External Paper Link:** `https://dl.acm.org/doi/10.1145/3653322` ### 15. Detecting Correct Answers to Open Questions and Its Impact on Language Models' Confidence Scores (2024) - **Venue:** LatinX in AI (LXAI) Research Workshop at NAACL 2024, Mexico City - **Citation:** Guido Ivetta, Hernán Maina, Luciana Benotti. (2024). "Detecting Correct Answers to Open Questions and Its Impact on Language Models' Confidence Scores." LatinX in AI Research Workshop at NAACL 2024. - **Summary:** Explores how the automatic detection of correct open-ended answers influences model confidence scoring and calibration in Large Language Models. - **URL:** `https://guidoivetta.github.io/publication/2024-06-21-detecting-correct-answers-lxai` | **External Paper Link:** `https://doi.org/10.52591/lxai202406219` ### 16. CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark (2024) - **Venue:** Proceedings of the 38th International Conference on Neural Information Processing Systems (NeurIPS 2024) - **Citation:** David Romero, Chenyang Lyu, Haryo Akbarianto Wibowo, Teresa Lynn, Injy Hamed, ..., Guido Ivetta, ..., Thamar Solorio, Alham Fikri Aji. (2024). "CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark." NeurIPS 2024. - **Summary:** 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. - **URL:** `https://guidoivetta.github.io/publication/2024-06-10-cvqa-multilingual-vqa` | **External Paper Link:** `https://dl.acm.org/doi/10.5555/3737916.3738282` ### 17. Your Stereotypical Mileage May Vary: Practical Challenges of Evaluating Biases in Multiple Languages and Cultural Contexts (2024) - **Venue:** Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024) - **Citation:** Karën Fort, Laura Alonso Alemany, Luciana Benotti, Julien Bezançon, ..., Guido Ivetta, ..., Aurélie Névéol. (2024). "Your Stereotypical Mileage May Vary: Practical Challenges of Evaluating Biases in Multiple Languages and Cultural Contexts." LREC-COLING 2024, pp. 17764–17769. - **Summary:** 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. - **URL:** `https://guidoivetta.github.io/publication/2024-05-20-stereotypical-mileage-may-vary` | **External Paper Link:** `https://aclanthology.org/2024.lrec-main.1545/` ### 18. Inteligencia Artificial Aplicada a la Huerta Familiar Agroecológica en la Patagonia (2023) - **Venue:** Revista de Ciencias Sociales, Universidad Nacional de Quilmes (UNQ) - **Citation:** Luciana Benotti, Marcela Properzi, Guido Ivetta, et al. (2023). "Inteligencia artificial aplicada a la huerta familiar agroecológica en la Patagonia." Revista de Ciencias Sociales, UNQ. - **Summary:** Artículo publicado en la Revista de Ciencias Sociales (UNQ) sobre la aplicación situada de herramientas de inteligencia artificial para huertas agroecológicas en la Patagonia. - **URL:** `https://guidoivetta.github.io/publication/2023-03-15-ia-huerta-agroecologica-revista-unq` | **External Paper Link:** `https://ediciones.unq.edu.ar/publicaciones/editorial/publicaciones-periodicas/revista-de-ciencias-sociales-segunda-epoca.html` ### 19. Aprendizaje Automático Aplicado a la Huerta Familiar Agroecológica en la Patagonia (2023) - **Venue:** Tesina de Licenciatura en Ciencias de la Computación, FaMAF, Universidad Nacional de Córdoba - **Citation:** Guido Ivetta, Luciana Benotti. (2023). "Aprendizaje Automático Aplicado a la Huerta Familiar Agroecológica en la Patagonia." Tesina de Licenciatura en Ciencias de la Computación, FaMAF, Universidad Nacional de Córdoba. - **Summary:** Tesina de Licenciatura en Ciencias de la Computación sobre técnicas de machine learning aplicadas al manejo agroecológico de huertas familiares. - **URL:** `https://guidoivetta.github.io/publication/2023-03-01-aprendizaje-automatico-huerta-tesina` | **External Paper Link:** `https://www.sidalc.net/search/Record/dig-unc-ar-11086-546994/Description` ### 20. A Methodology to Characterize Bias and Harmful Stereotypes in Natural Language Processing in Latin America (2022) - **Venue:** arXiv preprint arXiv:2207.06591 - **Citation:** Laura Alonso Alemany, Luciana Benotti, Hernán Maina, ..., Guido Ivetta, ..., Beatriz Busaniche. (2022). "A Methodology to Characterize Bias and Harmful Stereotypes in Natural Language Processing in Latin America." arXiv:2207.06591. - **Summary:** Presents a pioneering methodology to characterize harmful stereotypes and demographic biases across Spanish language technologies in Latin America. - **URL:** `https://guidoivetta.github.io/publication/2022-07-14-methodology-characterize-bias-latin-america` | **External Paper Link:** `https://arxiv.org/abs/2207.06591` --- ## 5. Invited Talks, Tutorials & Conference Presentations - **Practical Workshop on Socio-Cultural AI Evaluation** (Practical Workshop Leader, *Second South American NLP School, Universidad de Buenos Aires (UBA)*, Buenos Aires, Argentina, August 2026): Hands-on workshop leader instructing on evaluating socio-cultural biases, regional stereotypes, and calibration in language models. - **Adaptive Data Collection for Latin-American Community-sourced Evaluation of Stereotypes (LACES)** (Conference Presentation & Workshop Oral, *63rd Annual Meeting of the Association for Computational Linguistics (ACL 2026)*, San Diego, USA, July 2026): Findings poster, oral presentation at StereACuLT workshop, and co-organizer of BoF 'Who Gets Left Behind? Identity, Culture, and Power in NLP Systems'. - **Logical Reasoning Evaluation and Social Bias** (Workshop Talk, *ICLR 2026 Workshop on Logical Reasoning of Large Language Models*, Singapore, May 2026): Talk examining the interaction between formal logical reasoning in LLMs and socio-cultural bias traces. - **Logical Reasoning Evaluation and Social Bias** (Featured Workshop Oral & Poster, *ICLR 2026 Workshop on Logical Reasoning of Large Language Models*, Rio de Janeiro, Brazil, April 2026): Oral and poster presentation selected as a featured work at the ICLR 2026 Logical Reasoning Workshop. - **HESEIA at the India AI Impact Summit 2026** (Poster & Symposium Presentation, *India AI Impact Summit 2026 (AI Research & Impact Symposium)*, New Delhi, India, February 2026): Presented HESEIA and participatory community co-design methodologies for evaluating social biases in LLMs. - **Insights from a Disaggregated Analysis of Kinds of Biases in a Multicultural Dataset** (Workshop Presentation, *9th Widening NLP Workshop (WiNLP 2025)*, Online / Suzhou, November 2025): Presentation on fine-grained disaggregated evaluation of specific stereotypes in multicultural datasets. - **HESEIA: A Community-Based Dataset for Evaluating Social Biases in Large Language Models** (Oral & Poster Presentation, *Conference on Empirical Methods in Natural Language Processing (EMNLP 2025)*, Suzhou, China, November 2025): Main conference oral and poster presentation at EMNLP 2025 in Suzhou, China. - **Navigating Ethical Challenges in NLP: Hands-on Strategies for Students and Researchers** (Tutorial, *63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)*, Vienna, Austria, July 2025): Tutorial at ACL 2025 covering ethical issues in NLP, hands-on strategies for evaluation, and responsible research practices. - **Socio-Cultural Evaluation of AI** (Practical Session & Tutorial, *Khipu: Latin American Meeting in Artificial Intelligence*, Latin America, March 2025): Hands-on tutorial and practical session on socio-cultural evaluation of stereotypes and biases in language models. - **Detecting Correct Answers to Open Questions and Its Impact on Language Models' Confidence Scores** (Oral Presentation, *LatinX in AI (LXAI) Research Workshop at NAACL 2024*, Mexico City, Mexico, June 2024): Presentation on calibration, uncertainty estimation, and evaluation of open question answering in LLMs. - **EDIA: Evaluation of Bias for Experts in Discrimination, Not in Computer Science** (Tutorial & CRAFT Session, *ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT 2024)*, Rio de Janeiro, Brazil, June 2024): Interactive tutorial and CRAFT session on auditing social biases in NLP using the open-source EDIA tool. - **Workshop on Responsible AI & Bias Evaluation** (Workshop Organizer & Speaker, *FaMAF, Universidad Nacional de Córdoba*, Córdoba, Argentina, May 2024): Main organizer and speaker; awarded KhipuX / Americas Fund grantee funding. - **Evaluating Bias in Language Models with the EDIA Tool** (Workshop Speaker & Tool Demo, *RightsCon 2023*, San José, Costa Rica, June 2023): Tool demonstration and workshop on identifying algorithmic bias with EDIA. --- ## 6. Teaching, Thesis Advising & Academic Service - **Assistant Professor (*Profesor Asistente*) in Computer Science**, FaMAF, Universidad Nacional de Córdoba (March 2021 – Present): - *Databases (Bases de Datos)* - *Discrete Mathematics II (Matemática Discreta II)* - *Introduction to Logic (Introducción a la Lógica)* - **Undergraduate Thesis Supervision (Director de Trabajo Final de Licenciatura)**: - **Lic. Sofía Martinelli** (Defended December 2025, FaMAF UNC): *"Sesgos en modelos de lenguaje y construcción participativa de benchmarks de evaluación"* (`https://rdu.unc.edu.ar/items/7fff7b3e-3df3-4bac-a91a-9d50e83c8700`). Led directly to the Featured Paper at ICLR 2026 Workshop and co-authored papers at EMNLP 2025 and ACL 2026. - **Thesis Examination Committees (*Jurado de Tesis de Grado*, FaMAF UNC)**: - Evaluator for Licenciatura en Ciencias de la Computación theses by María Victoria López Amuchastegui, Nicolás András Hormann Manriquez, and Tiffany Bricet Fuentes de Abreu. - **International Scientific Service**: - Student Member of the **ACL Ethics Committee** (September 2024 – Present). - Co-Organizer of the Birds-of-a-Feather Session *"Who Gets Left Behind? Identity, Culture, and Power in NLP Systems"* at **ACL 2026** (San Diego, USA) alongside Dr. Alberto Testoni (Amsterdam UMC). - Co-Instructor of the **ACL 2025 Tutorial** *"Navigating Ethical Challenges in NLP"* (Vienna, Austria). - Practical Session Instructor at **Khipu 2025** Latin American Meeting in Artificial Intelligence (Santiago, Chile) and **Second South American NLP School** at Universidad de Buenos Aires (August 2026). - Tutorial Instructor at **ACM FAccT 2024** (Rio de Janeiro, Brazil) and **RightsCon 2023** (San José, Costa Rica).