000599188 001__ 599188
000599188 005__ 20231128212231.0
000599188 037__ $$aPUBDB-2023-07212
000599188 041__ $$aEnglish
000599188 1001_ $$0P:(DE-H253)PIP1096696$$aSulc, Antonin$$b0$$eCorresponding author$$udesy
000599188 1112_ $$aNeurIPS 2023 workshop on Machine Learning and the Physical Sciences$$cNew Orleans$$d2023-12-15 - 2023-12-15$$gNeuralIPS2023$$wUSA
000599188 245__ $$aPACuna: Automated Fine-Tuning of Language Models for Particle Accelerators
000599188 260__ $$c2023
000599188 300__ $$a7
000599188 3367_ $$2ORCID$$aCONFERENCE_PAPER
000599188 3367_ $$033$$2EndNote$$aConference Paper
000599188 3367_ $$2BibTeX$$aINPROCEEDINGS
000599188 3367_ $$2DRIVER$$aconferenceObject
000599188 3367_ $$2DataCite$$aOutput Types/Conference Paper
000599188 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1701176125_2750837
000599188 520__ $$aNavigating the landscape of particle accelerators has become increasingly challenging with recent surges in contributions. These intricate devices challenge comprehension, even within individual facilities.To address this, we introduce PACuna, a fine-tuned language model refined through publicly available accelerator resources like conferences, pre-prints, and books.We automated data collection and question generation to minimize expert involvement and make the code available.PACuna demonstrates proficiency in addressing accelerator questions validated by experts.Our approach shows adapting language models to scientific domains by fine-tuning technical texts and auto-generated corpora capturing the latest developments can further produce pre-trained models to answer some specific questions that commercially available assistants cannot and can serve as intelligent assistants for individual facilities.
000599188 536__ $$0G:(DE-HGF)POF4-621$$a621 - Accelerator Research and Development (POF4-621)$$cPOF4-621$$fPOF IV$$x0
000599188 693__ $$0EXP:(DE-H253)XFEL(machine)-20150101$$1EXP:(DE-H253)XFEL-20150101$$5EXP:(DE-H253)XFEL(machine)-20150101$$aXFEL$$eFacility (machine) XFEL$$x0
000599188 7001_ $$0P:(DE-H253)PIP1002321$$aKammering, Raimund$$b1$$udesy
000599188 7001_ $$0P:(DE-H253)PIP1087213$$aEichler, Annika$$b2$$udesy
000599188 7001_ $$0P:(DE-H253)PIP1007238$$aWilksen, Tim$$b3$$udesy
000599188 8564_ $$uhttps://bib-pubdb1.desy.de/record/599188/files/NeurIPS_2023_LLM.pdf$$yRestricted
000599188 8564_ $$uhttps://bib-pubdb1.desy.de/record/599188/files/NeurIPS_2023_LLM.pdf?subformat=pdfa$$xpdfa$$yRestricted
000599188 909CO $$ooai:bib-pubdb1.desy.de:599188$$pVDB
000599188 9101_ $$0I:(DE-588b)2008985-5$$6P:(DE-H253)PIP1096696$$aDeutsches Elektronen-Synchrotron$$b0$$kDESY
000599188 9101_ $$0I:(DE-588b)2008985-5$$6P:(DE-H253)PIP1002321$$aDeutsches Elektronen-Synchrotron$$b1$$kDESY
000599188 9101_ $$0I:(DE-588)1043621512$$6P:(DE-H253)PIP1002321$$aEuropean XFEL$$b1$$kXFEL.EU
000599188 9101_ $$0I:(DE-588b)2008985-5$$6P:(DE-H253)PIP1087213$$aDeutsches Elektronen-Synchrotron$$b2$$kDESY
000599188 9101_ $$0I:(DE-588)1043621512$$6P:(DE-H253)PIP1087213$$aEuropean XFEL$$b2$$kXFEL.EU
000599188 9101_ $$0I:(DE-588b)2008985-5$$6P:(DE-H253)PIP1007238$$aDeutsches Elektronen-Synchrotron$$b3$$kDESY
000599188 9131_ $$0G:(DE-HGF)POF4-621$$1G:(DE-HGF)POF4-620$$2G:(DE-HGF)POF4-600$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bForschungsbereich Materie$$lMaterie und Technologie$$vAccelerator Research and Development$$x0
000599188 9141_ $$y2023
000599188 9201_ $$0I:(DE-H253)MCS_4-20120731$$kMCS 4$$lBeschleunigerkontrollen (FLASH/XFEL)$$x0
000599188 980__ $$acontrib
000599188 980__ $$aVDB
000599188 980__ $$aI:(DE-H253)MCS_4-20120731
000599188 980__ $$aUNRESTRICTED