Publications

Peer-reviewed

• Favero, L., Pérez-Ortiz, J. A., Käser, T., & Oliver, N. (2026).

  From Substitution to Scaffolding: Breaking the Self-Reinforcing Harm Cycle of AI in Education (and Beyond)

  ACM AI Leadership Summit 2026 · To be published

• Favero, L., Pérez-Ortiz, J. A., Käser, T., & Oliver, N. (2026).

  MAIKE: Designing a Socratic Educational Chatbot to Foster Critical Thinking and Learner Agency

  Tools for Thought workshop at ACM CHI 2026, Barcelona, Spain

  • PDF
  • Code
  • Project

• Favero, L., Pérez-Ortiz, J. A., Käser, T., & Oliver, N. (2026).

  Leveraging Small LLMs for Argument Mining in Education: Argument Component Identification, Classification, and Assessment

  Proceedings of the 25th International Workshop on Computational Models of Natural Argument (CMNA 2025), CEUR-WS Vol-4166, pp. 11–30

  • PDF
  • arXiv

• Favero, L., Frases, D., Pérez-Ortiz, J. A., Käser, T., & Oliver, N. (2025).

  ELLIS Alicante at CQs-Gen 2025: Winning the Critical Thinking Questions Shared Task: LLM-Based Question Generation and Selection

  Proceedings of the 12th Workshop on Argument Mining (ArgMining 2025), ACL 2025, Vienna, Austria

  ★ Winner of the Critical Questions Generation Shared Task, ranked 1st of 13 international teams

  • ACL Anthology
  • DOI
  • arXiv
  • Press release

• Favero, L., Pérez-Ortiz, J. A., Käser, T., & Oliver, N. (2025).

  Do AI Tutors Empower or Enslave Learners? Toward a Critical Use of AI in Education

  Applications of Generative AI to Support Teaching and Learning in Higher Education (GenAIHEd), workshop at AIED 2025, Palermo, Italy · Selected as the workshop's opening talk

  • arXiv
  • Workshop

• Favero, L., Pérez-Ortiz, J. A., Käser, T., & Oliver, N. (2025).

  Argument Mining in Education: Exploring the Potential of Open-Source Small LLMs for Argument Classification and Assessment

  AI for Education: Tools, Opportunities, and Risks in the Generative AI Era (AI4ED), workshop at AAAI 2025, Philadelphia, USA

  • PDF
  • Workshop

• Favero, L., Pérez-Ortiz, J. A., Käser, T., & Oliver, N. (2024).

  Enhancing Critical Thinking in Education by Means of a Socratic Chatbot

  Proceedings of the 1st International Workshop on AI in Education and Educational Research (AIEER 2024), ECAI 2024, Santiago de Compostela, Spain. Springer CCIS · Cited 140+ times (Google Scholar, Aug 2026)

  • DOI

• Favero, L., Pérez-Ortiz, J. A., Käser, T., & Oliver, N. (2024).

  Towards Student-Centric AI-Supported Learning: Teaching Chatbots to Ask the Right Questions

  Collaborative AI and Modeling of Humans (CAIHu) Bridge, AAAI 2024, Vancouver, Canada

  • Workshop

Preprints and under review

• Favero, L., Pérez-Ortiz, J. A., Käser, T., & Oliver, N. (2026).

  Score the Construct, Not the Average: How Trait-Level Ordinal Essay Scoring Recovers Writers Who Need It Most

  Under review

• Favero, L., Gaudeau, G., Pérez-Ortiz, J. A., Käser, T., & Oliver, N. (2026).

  Argumentative Essay Assessment with LLMs: A Critical Scoping Review

  Research Square preprint (rs-8632843) · PRISMA 2020-conformant review of 46 studies (2022–2025) across six dimensions: datasets, traits, models, methods, evaluation, and analytics

  • Preprint

• Favero, L., Pérez-Ortiz, J. A., Käser, T., & Oliver, N. (2026).

  Beyond Holistic Scores: Automatic Trait-Based Quality Scoring of Argumentative Essays

  arXiv preprint arXiv:2602.04604 · Evaluates a structured in-context-learning small-LLM pipeline against a supervised BigBird encoder with CORAL-style ordinal regression on 1,783 essays from the ASAP++ benchmark

  • arXiv

• Favero, L., Pérez-Ortiz, J. A., Käser, T., & Oliver, N. (2026).

  AI in Education Beyond Learning Outcomes: Cognition, Agency, Emotion, and Ethics

  arXiv preprint arXiv:2602.04598 · Position paper proposing an integrative four-dimensional framework for evaluating AI in education

  • arXiv

Posters

• Favero, L., Frases, D., Pérez-Ortiz, J. A., Käser, T., & Oliver, N. (2025).

  ELLIS Alicante at CQs-Gen 2025: Winning the Critical Thinking Questions Shared Task: LLM-Based Question Generation and Selection

  12th Workshop on Argument Mining, ACL 2025, Vienna, Austria

  ★ Winner of the shared task (1st of 13 teams)

  • arXiv

• Favero, L., Frases, D., Pérez-Ortiz, J. A., Käser, T., & Oliver, N. (2025).

  Critical Thinking Questions Shared Task: LLM-Based Generation and Judgement

  Jornada del Doctorado en Informática, Universidad de Alicante, Spain

  • Poster PDF

• Derner, E., Sansalvador de la Fuente, S., Gutiérrez, Y., Moreda, P., & Oliver, N. (presenter: Favero, L.) (2025).

  Leveraging Large Language Models to Measure Gender Representation Bias in Gendered Language Corpora

  CAIHu Bridge, AAAI 2025, Philadelphia, USA

• Favero, L., Pérez-Ortiz, J. A., Käser, T., & Oliver, N. (2024).

  Enhancing Critical Thinking in Education with a Socratic Chatbot

  ELLIS Doctoral Symposium, Paris, France

• Favero, L., Pérez-Ortiz, J. A., Käser, T., & Oliver, N. (2024).

  Enhancing Critical Thinking in Education with a Socratic Chatbot

  Jornada del Doctorado en Informática, Universidad de Alicante, Spain

  ★ Best Poster Award

  • Poster PDF

• Favero, L., Pérez-Ortiz, J. A., Käser, T., & Oliver, N. (2024).

  Towards Student-Centric AI-Supported Learning: Teaching Chatbots to Ask the Right Questions

  CAIHu Bridge, AAAI 2024, Vancouver, Canada

• Derner, E., Kučera, D., Oliver, N., & Zahálka, J. (presenter: Favero, L.) (2024).

  Can ChatGPT Read Who You Are?

  CAIHu Bridge, AAAI 2024, Vancouver, Canada