% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@INPROCEEDINGS{Sulc:599188,
author = {Sulc, Antonin and Kammering, Raimund and Eichler, Annika
and Wilksen, Tim},
title = {{PAC}una: {A}utomated {F}ine-{T}uning of {L}anguage
{M}odels for {P}article {A}ccelerators},
reportid = {PUBDB-2023-07212},
pages = {7},
year = {2023},
abstract = {Navigating the landscape of particle accelerators has
become increasingly challenging with recent surges in
contributions. These intricate devices challenge
comprehension, even within individual facilities.To address
this, we introduce PACuna, a fine-tuned language model
refined through publicly available accelerator resources
like conferences, pre-prints, and books.We automated data
collection and question generation to minimize expert
involvement and make the code available.PACuna demonstrates
proficiency in addressing accelerator questions validated by
experts.Our approach shows adapting language models to
scientific domains by fine-tuning technical texts and
auto-generated corpora capturing the latest developments can
further produce pre-trained models to answer some specific
questions that commercially available assistants cannot and
can serve as intelligent assistants for individual
facilities.},
month = {Dec},
date = {2023-12-15},
organization = {NeurIPS 2023 workshop on Machine
Learning and the Physical Sciences, New
Orleans (USA), 15 Dec 2023 - 15 Dec
2023},
cin = {MCS 4},
cid = {$I:(DE-H253)MCS_4-20120731$},
pnm = {621 - Accelerator Research and Development (POF4-621)},
pid = {G:(DE-HGF)POF4-621},
experiment = {EXP:(DE-H253)XFEL(machine)-20150101},
typ = {PUB:(DE-HGF)8},
url = {https://bib-pubdb1.desy.de/record/599188},
}