LLM cross-model alignment measurement and improvement
Organisatsiooni nimi
TartuNLP
Kokkuvõte
It has been shown that independently trained LLMs (GPT, BERT, etc) learn input vector representations that have a certain structure, similar between the different models. The aim of this thesis is to measure this similarity (or "alignment") between pre-trained models, in-training models and possibly integrate alignment into the training process as an optimization objective.
Lõputöö kaitsmise aasta
2023-2024
Juhendaja
Mark Fishel
Suhtlemiskeel(ed)
eesti keel, inglise keel
Nõuded kandideerijale
Python, pytorch, transformers, vector space transformations and metrics
Tase
Magister
Märksõnad
Kandideerimise kontakt
Nimi
Mark Fishel
Tel
E-mail