Scholar
Simone Balloccu
Google Scholar ID: O-eIjBAAAAAJ
TU Darmstadt
Citations & Impact
Citations
506
H-index
9
i10-index
9
Publications
20
Co-authors
18
list available
Publications
Resume (English only)
Academic Achievements
- - INLG 2024 paper, “Automatic Metrics in Natural Language Generation: A Survey of Current Evaluation Practices,” won the “Best Evaluation Paper” award
- - EACL 2024 paper, “Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs,” won the “Best Non Publicized Paper” award
- - Published “Anno-MI: A Dataset of Expert-Annotated Counselling Dialogues” at ICASSP 2022
- - Published “Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs” at EACL 2024
Research Experience
- - Junior lab leader of the “NLP for Expert Domains” (ExpNLP) group at TU Darmstadt
- - Postdoc at Charles University (CZ) within the ERC-funded “NG-NLG” project, covering controllability of neural approaches to text generation
Education
- - PhD: University of Aberdeen (UK), Marie-Curie ESR, within the H2020 “Philhumans” project, working on efficient healthcare communication
- - Undergraduate: Università degli studi di Cagliari (IT), worked on unsupervised NLP and business-oriented data mining
Background
- - Computer scientist with 6+ years of experience in NLP & AI research
- - Involved in several EU-funded projects, including Horizon 2020, ERC, and EU Erasmus Traineeship
- - Focus on AI for mental health and behavior change, safety and controllability evaluation, and more generally on AI applied to expert domains
- - Extensive experience in the human evaluation of AI
- - Currently leading the “NLP for expert domains” group at TU Darmstadt, focused on the cooperation between AI agents and domain experts
Miscellany
- - Personal interests and hobbies not mentioned
