These webpages contain theses and reports by students affiliated with the various bachelor and master programmes offered at the Leiden Institute of Advanced Computer Science
(LIACS),
the computer science and artificial intelligence department of Leiden University.
Note: this thesis repository might be incomplete for certain programmes and years.
The following thesis was written by a student in the 2024-2025 class of the Bachelor Data Science and Artificial Intelligence programme at Leiden University.
Thesis details
Title | Reinforcement Learning for Training Small LLMs by Distillation |
Student | Li, X. (Xu) |
Programme | Bachelor Data Science and Artificial Intelligence |
Year | 2024-2025 |
Supervisors | Plaat, prof.dr. A. (Aske) Stein, dr. N. (Niki) van |
Thesis | Open Thesis PDF |
Citation details
Li, X. (Xu), Reinforcement Learning for Training Small LLMs by Distillation, Thesis Bachelor Data Science and Artificial Intelligence, LIACS, Leiden University, 2025.