{"id":"https://openalex.org/W7130593194","doi":"https://doi.org/10.1109/fllm67465.2025.11391123","title":"Fine-Tuning Large Language Models for Vocabulary-Constrained Language Learning","display_name":"Fine-Tuning Large Language Models for Vocabulary-Constrained Language Learning","publication_year":2025,"publication_date":"2025-11-25","ids":{"openalex":"https://openalex.org/W7130593194","doi":"https://doi.org/10.1109/fllm67465.2025.11391123"},"language":null,"primary_location":{"id":"doi:10.1109/fllm67465.2025.11391123","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm67465.2025.11391123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 3rd International Conference on Foundation and Large Language Models (FLLM)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107099321","display_name":"Jens Wienkamp","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105785","display_name":"Intelligent Systems Research (United States)","ror":"https://ror.org/01reevc91","country_code":"US","type":"company","lineage":["https://openalex.org/I4210105785"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jens Wienkamp","raw_affiliation_strings":["University of Münster,Autonomous Intelligent Systems Group,Münster,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Münster,Autonomous Intelligent Systems Group,Münster,Germany","institution_ids":["https://openalex.org/I4210105785"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011185444","display_name":"Malte Schilling","orcid":"https://orcid.org/0000-0002-0849-483X"},"institutions":[{"id":"https://openalex.org/I4210105785","display_name":"Intelligent Systems Research (United States)","ror":"https://ror.org/01reevc91","country_code":"US","type":"company","lineage":["https://openalex.org/I4210105785"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Malte Schilling","raw_affiliation_strings":["University of Münster,Autonomous Intelligent Systems Group,Münster,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Münster,Autonomous Intelligent Systems Group,Münster,Germany","institution_ids":["https://openalex.org/I4210105785"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210105785"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.6886235,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"443","last_page":"448"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.30799999833106995,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.30799999833106995,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.17520000040531158,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.16220000386238098,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.8381999731063843},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6211000084877014},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5684999823570251},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4894999861717224},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4700999855995178},{"id":"https://openalex.org/keywords/language-acquisition","display_name":"Language acquisition","score":0.38019999861717224}],"concepts":[{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.8381999731063843},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7394000291824341},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6211000084877014},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5684999823570251},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5666000247001648},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5121999979019165},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4894999861717224},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4700999855995178},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.38019999861717224},{"id":"https://openalex.org/C2984601542","wikidata":"https://www.wikidata.org/wiki/Q48842322","display_name":"Vocabulary learning","level":3,"score":0.3352000117301941},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.3255000114440918},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C2779313563","wikidata":"https://www.wikidata.org/wiki/Q17072565","display_name":"On Language","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fllm67465.2025.11391123","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm67465.2025.11391123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 3rd International Conference on Foundation and Large Language Models (FLLM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8092010021209717,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1488996941","https://openalex.org/W3105234097","https://openalex.org/W4385287322","https://openalex.org/W4385572399","https://openalex.org/W4389519496","https://openalex.org/W4389523854","https://openalex.org/W4392931630","https://openalex.org/W4396823873","https://openalex.org/W4402671611","https://openalex.org/W4406687569","https://openalex.org/W4412993377"],"related_works":[],"abstract_inverted_index":{"This":[0],"study":[1,44],"explores":[2],"techniques":[3],"for":[4,45,112,128],"constraining":[5],"the":[6,38,57,61,65,107,123,133],"output":[7],"of":[8,67,74,109,125,135],"Large":[9],"Language":[10],"Models":[11],"(LLMs)":[12],"to":[13,95],"a":[14,19,42,52],"predefined":[15],"vocabulary":[16,63,75,91],"which":[17],"is":[18],"critical":[20],"requirement":[21],"in":[22],"early-stage":[23],"language":[24,130],"learning.":[25],"We":[26],"evaluate":[27],"two":[28],"approaches\u2014prompt":[29],"engineering":[30,86],"and":[31,36,64,77,105,132],"parameter-efficient":[32],"fine-tuning\u2014comparing":[33],"different":[34],"models":[35,89],"using":[37],"LLaMA-3-8B-Instruct":[39],"model":[40],"as":[41],"case":[43],"fine-tuning.":[46],"To":[47],"measure":[48],"success,":[49],"we":[50],"introduce":[51],"custom":[53],"metric":[54],"that":[55,83],"quantifies":[56],"exact":[58],"match":[59],"between":[60],"used":[62],"set":[66],"already":[68],"introduced":[69],"words,":[70],"enabling":[71],"precise":[72],"evaluation":[73,137],"adherence":[76,104],"fine-tuning":[78,101],"progress.":[79],"Experimental":[80],"results":[81],"show":[82],"while":[84],"prompt":[85],"can":[87],"guide":[88],"toward":[90],"restrictions,":[92],"it":[93],"fails":[94],"achieve":[96],"consistent":[97],"compliance.":[98],"In":[99],"contrast,":[100],"yields":[102],"near-perfect":[103],"demonstrates":[106],"utility":[108],"auxiliary":[110],"metrics":[111],"preventing":[113],"overfitting,":[114],"outperforming":[115],"loss-based":[116],"monitoring":[117],"alone.":[118],"These":[119],"findings":[120],"highlight":[121],"both":[122],"potential":[124],"fine-tuned":[126],"LLMs":[127],"controlled":[129],"generation":[131],"importance":[134],"taskspecific":[136],"methods.":[138]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-02-20T00:00:00"}