From the 6 of 57 papers with an AI index.
3 citations
- Centre National de la Recherche ScientifiqueFR5 papers
- ETH ZurichCH4 papers
- National Institute for AstrophysicsIT3 papers
- University of PaduaIT3 papers
- Astronomical Observatory of RomeIT2 papers
- Centre de Physique ThéoriqueFR2 papers
- Delft University of TechnologyNL2 papers
- Institute for Cross-Disciplinary Physics and Complex SystemsES2 papers
- Institute of Structure of MatterIT2 papers
- Istituto Nazionale di Fisica Nucleare, Sezione di MilanoIT2 papers
- Politecnico di TorinoIT2 papers
- Sorbonne UniversitéFR2 papers
3 papers · 1 filter
Automatic identification of diagnosis from hospital discharge letters via weakly supervised Natural Language Processing
Vittorio Torri, Elisa Barbieri, Anna Cantarutti +2
Identifying patient diagnoses from hospital discharge letters is essential for large-scale cohort selection and epidemiological research, but traditional supervised approaches requ…
Multiple Choice Questions: Reasoning Makes Large Language Models (LLMs) More Self-Confident, Especially When They are Wrong
Tairan Fu, Javier Conde, Gonzalo MartÃnez +2
Multiple Choice Question (MCQ) tests are among the most used methods for evaluating large language models (LLMs). Besides checking the correctness of the selected answer, evaluatio…
EmbBERT: Attention Under 2 MB Memory
Riccardo Bravin, Massimo Pavan, Hazem Hesham Yousef Shalby +2
Transformer architectures based on the attention mechanism have revolutionized natural language processing (NLP), driving major breakthroughs across virtually every NLP task. Howev…