Pietro Lesci
- PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs
2025/03/12 by Oskar van der Wal, van der Wal, Oskar, Pietro Lesci +11 · 2 voices · 12 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques
- What Language is This? Ask Your Tokenizer
2026/02/19 by Clara Meister, Ahmetcan Yavuz, Pietro Lesci +1 · 3 voices
#cs.CL
- Self-Training Large Language Models for Tool-Use Without Demonstrations
2025/02/09 by Nuan Luo, Aryo Pradipta Gema, Luo, Ne +9 · 3 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning and Data Classification #Natural Language Processing Techniques #Topic Modeling
- Causal Estimation of Tokenisation Bias
2025/06/03 by Pietro Lesci, Lesci, Pietro, Clara Meister +7 · 2 voices · 2 citations
#cs.CL #cs.AI #cs.LG