Eliseo Bao
I am a Ph.D. student in Computer Science at the Information Retrieval Laboratory (IRLab), CITIC, University of A Coruña, advised by Javier Parapar and Anxo Pérez.
My research sits at the intersection of Natural Language Processing and mental health. I work on detecting and explaining depression-related symptoms in social media text against clinical frameworks such as the DSM-5 and the Beck Depression Inventory-II (BDI-II), and on building conversational agents that support rather than replace clinicians. More recently, I have been extending this line of work into evaluating how faithfully LLM-based personas can simulate real users, towards safer and more realistic mental-health research tools.
In late 2025, I was a visiting researcher at the University of Sheffield, working with Xi Wang on persona simulation.
news
| Oct 28, 2026 | Presented “Artificial Intelligence and Mental Health: What Can Social Media Tell Us?” with Anxo Pérez Vila at the Faculty of Computer Science, Universidade da Coruña, as part of 12th Healthy October programme. |
|---|---|
| Oct 22, 2026 | Served as a mentor at Datathon Justicia 2026 on 21–22 October, supporting the Childhood and Youth challenge. |
| Sep 25, 2026 | Participated in G-Night / European Researchers’ Night, contributing to science outreach at Universidade da Coruña. |
| Jul 24, 2026 | Two papers this July: “Improving clinical reliability of LLM reasoning for depression assessment via structured generation and GRPO” in Science Progress, and “Learning Evidence of Depression Symptoms via Prompt Induction” at SIGIR 2026 in Melbourne, Australia. |
| May 19, 2026 | Gave an invited talk, “Explainable AI for Depression Symptom Detection on Social Media,” at International University of La Rioja (UNIR), presenting explainable AI for depression symptom detection and the MindWell conversational agent. |