Publications

(2026). A Text Mining and Classification Approach for Analyzing Architecture Decision Records. Proceedings of the 20th European Conference on Software Architecture (ECSA 2026), Bolzano, Italy.

Preprint PDF

(2026). A Surrogate-based Approach for Fast Multi-objective Architectural Refactoring Optimization. Proceedings of the 20th European Conference on Software Architecture (ECSA 2026), Bolzano, Italy.

Preprint PDF

(2026). Training seeds and model-selection stability in recommender-system evaluation. _Proceedings of the 20th ACM Conference on Recommender Systems (RecSys 2026), Minneapolis, United States, https://doi.org/10.1145/3773078.3841289_.

PDF Source Document

(2026). Measuring Human-Like Bias in LLMs? A Critique of Human-Derived Bias Constructs in LLM Evaluation. Findings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026), Budapest, Hungary.

PDF

(2026). Distilling Multilingual Models for Few-Shot Gender-Bias Detection in Spanish Judicial Texts: A Systematic Literature Review. Proceedings of the Argentine Symposium on Artificial Intelligence and Data Science (ASAID), 55th JAIIO 2026, La Plata, Argentina.

PDF Source Document

(2026). A Hybrid RAG for Answering Questions about Technical Documentation from Github Projects. Proceedings of the Argentine Symposium on Software Engineering (ASSE), 55th JAIIO 2026, La Plata, Argentina.

PDF Source Document

(2026). How Prompting Shapes LLM-Generated Explanations for Recommender Systems: A Multi-Prompt Comparison Across Domains. Joint Proceedings of the ACM UMAP Workshops 2026 — Workshop on Explainable User Models and Personalized Systems (ExUM 2026), pp. 1-9.

PDF Source Document

(2026). From emotional hooks to conspiratorial claims: A teen-focused game for reflecting on misinformation interactions. _Proceedings of the 34th ACM Conference on User Modeling, Adaptation and Personalization (UMAP 2026), Gothenburg, Sweden, https://doi.org/10.1145/3774935.3812727_.

PDF Source Document

(2026). REFLECT: Tutorial on Reflecting on Bias in LLMs through Human-Centered Perspectives. _Companion Proceedings of the 31st International Conference on Intelligent User Interfaces (IUI 2026), pp. 286-288, https://doi.org/10.1145/3742414.3794952_.

PDF Source Document

(2026). Cognitive Effects and Biases in Large Language Models. _Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 6: Tutorial Abstracts), pp. 4-6, https://doi.org/10.18653/v1/2026.eacl-tutorials.2_.

PDF Source Document

(2026). Energy Footprint of Data Reduction Strategies for Recommender Systems. Recommender Systems for Sustainability and Social Good (RecSoGood 2026), Springer, Cham.

PDF

(2025). Una Arquitectura Híbrida Extensible para Sistemas IA-Ready. XXXI Congreso Argentino de Ciencias de la Computación (CACIC 2025), Viedma, Argentina, pp. 808-817.

PDF Source Document

(2025). How Much Longer?: Estimating Bus Arrival Times with Predictive Models. Proceedings of the Argentine Symposium on Artificial Intelligence and Data Science (ASAID), 54th JAIIO 2025, Buenos Aires, Argentina.

PDF

(2025). Architecture Exploration and Reflection Meet LLM-based Agents. _2025 IEEE 22nd International Conference on Software Architecture Companion (ICSA-C), Odense, Denmark, pp. 46-50, https://doi.org/10.1109/ICSA-C65153.2025.00015_.

PDF Source Document

(2024). Leveraging Monte Carlo Tree Search for Group Recommendation. _Proceedings of the 18th ACM Conference on Recommender Systems (RecSys 2024), Bari, Italy, pp. 1136-1141, https://doi.org/10.1145/3640457.3691713_.

PDF Source Document

(2024). Fairness Matters: A look at LLM-generated group recommendations. _Proceedings of the 18th ACM Conference on Recommender Systems (RecSys 2024), Bari, Italy, pp. 993-998, https://doi.org/10.1145/3640457.3688182_.

PDF Source Document

(2024). Arquitecturas para Aplicaciones con Inteligencia Artificial: Un Mapeo Sistemático de la Literatura. Proceedings of the Argentine Symposium on Software Engineering (ASSE), 53rd JAIIO 2024, Bahía Blanca, Argentina, pp. 28-41.

PDF Source Document

(2024). Towards Automated Fact-Checking: An Exploratory Study on Identifying Check-worthy Phrases for Verification. _Proceedings of the L Latin American Computer Conference (CLEI 2024), Bahía Blanca, Argentina, https://doi.org/10.1109/CLEI64178.2024.10700241_.

PDF Source Document

(2024). Detection of Gender Bias in Legal Texts Using Classification and LLMs. _Proceedings of the L Latin American Computer Conference (CLEI 2024), Bahía Blanca, Argentina, pp. 1-10, https://doi.org/10.1109/CLEI64178.2024.10700116_.

PDF Source Document

(2024). Beyond Words: A Preliminary Study for Multimodal Hate Speech Detection. _Proceedings of the L Latin American Computer Conference (CLEI 2024), Bahía Blanca, Argentina, https://doi.org/10.1109/CLEI64178.2024.10700167_.

PDF Source Document

(2023). The JavaScript Package Selection Task: A Comparative Experiment Using ChatGPT. _XLIX Latin American Computer Conference (CLEI 2023), La Paz, Bolivia, pp. 1-10, https://doi.org/10.1109/CLEI60451.2023.10345786_.

PDF Source Document

(2023). Re2Dan: Retrieval of Medical Documents for e-Health in Danish. _Proceedings of the 17th ACM Conference on Recommender Systems (RecSys 2023), Singapore, pp. 1208-1211, https://doi.org/10.1145/3604915.3610655_.

PDF Source Document

(2023). La eParticipación ciudadana: problemáticas y tecnologías hacia una relación bidireccional. Proceedings of the Argentine Symposium on Technology and Society (STS 2023), 52nd JAIIO, Buenos Aires, Argentina.

PDF Source Document

(2023). Detection of gender bias in judicial decisions. Derecho, Universidad y Justicia, 2(3), pp. 92-103.

PDF

(2022). Towards automated fact-checking: An exploratory study on the detection of checkable statements in Spanish. XLI International Conference of the Chilean Computer Science Society (SCCC 2022).

PDF Code Dataset Slides

(2021). A Deep Learning model for estimating parking space availability. XL International Conference of the Chilean Computer Science Society (SCCC 2021).

PDF Slides

(2021). Is my model biased? Exploring Unintended Bias in Misogyny Detection Tasks. 1st Workshop on Adverse Impacts and Collateral Effects of Artificial Intelligence Technologies @ IJCAI-2021.

PDF Source Document

(2018). Textual aggression detection through deep learning. Proceedings of the First Workshop on Trolling, Aggression and Cyberbullying (TRAC-2018), pp. 177–187.

PDF Source Document