SEVESO ANDREA

Role
Research fellow  
Academic disciplines
Sistemi di elaborazione delle informazioni (ING-INF/05)
Room:
  • U07, Floor: 2, Room: 2043

Publications

  • Mercorio, F., Mezzanzanica, M., Potertì, D., Serino, A., Seveso, A. (2026). A Benchmark to Evaluate LLMs’ Proficiency on Italian Student Competencies. In Machine Learning and Knowledge Discovery in Databases. Research Track and Applied Data Science Track European Conference, ECML PKDD 2025, Porto, Portugal, September 15–19, 2025, Proceedings, Part VIII (pp.292-309). Springer Berlin, Heidelberg [10.1007/978-3-662-72243-5_17]. Detail

  • Abdaljalil, S., Pallucchini, F., Seveso, A., Kurban, H., Mercorio, F., Serpedin, E. (2025). SAFE: A Sparse Autoencoder-Based Framework for Robust Query Enrichment and Hallucination Mitigation in LLMs. In EMNLP 2025 - 2025 Conference on Empirical Methods in Natural Language Processing, Findings of EMNLP 2025 (pp.9335-9346). Association for Computational Linguistics (ACL) [10.18653/v1/2025.findings-emnlp.496]. Detail

  • Mercorio, F., Pallucchini, F., Potertì, D., Serino, A., Seveso, A. (2025). SFAL: Semantic-Functional Alignment Scores for Distributional Evaluation of Auto-Interpretability in Sparse Autoencoders. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track (pp.576-583). Association for Computational Linguistics. Detail

  • Mercorio, F., Mezzanzanica, M., Potertì, D., Serino, A., Seveso, A. (2025). A Benchmark to Evaluate LLMs’ Proficiency on Italian Student Competencies. Intervento presentato a: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases - From 15 to 19 September 2025, Porto, Portugal. Detail

  • Seveso, A., Potertì, D., Federici, E., Mezzanzanica, M., Mercorio, F. (2025). ITALIC: An Italian Culture-Aware Natural Language Benchmark. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies
    (Volume 1: Long Papers), April 29 - May 4, 2025 (pp.1469-1478). Association for Computational Linguistics (ACL) [10.18653/v1/2025.naacl-long.68].
     Detail