{"id":"https://openalex.org/W4406892518","doi":"https://doi.org/10.1109/fllm63129.2024.10852489","title":"Keep it Local: Comparing Domain-Specific LLMs in Native and Machine Translated Text using Parallel Corpora on Political Conflict","display_name":"Keep it Local: Comparing Domain-Specific LLMs in Native and Machine Translated Text using Parallel Corpora on Political Conflict","publication_year":2024,"publication_date":"2024-11-26","ids":{"openalex":"https://openalex.org/W4406892518","doi":"https://doi.org/10.1109/fllm63129.2024.10852489"},"language":"en","primary_location":{"id":"doi:10.1109/fllm63129.2024.10852489","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm63129.2024.10852489","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 2nd International Conference on Foundation and Large Language Models (FLLM)","raw_type":"proceedings-article"},"type":"article","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/A5069844991","display_name":"Javier Osorio","orcid":"https://orcid.org/0000-0002-4548-7794"},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Javier Osorio","raw_affiliation_strings":["University of Arizona,School of Government and Public Policy,Tucson,United States"],"affiliations":[{"raw_affiliation_string":"University of Arizona,School of Government and Public Policy,Tucson,United States","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079025806","display_name":"Sultan Alsarra","orcid":null},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Sultan Alsarra","raw_affiliation_strings":["King Saud University,Department of Software Engineering,Riyadh,Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"King Saud University,Department of Software Engineering,Riyadh,Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116057055","display_name":"Amber Converse","orcid":null},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amber Converse","raw_affiliation_strings":["University of Arizona,Department of Linguistics,Tucson,United States"],"affiliations":[{"raw_affiliation_string":"University of Arizona,Department of Linguistics,Tucson,United States","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024333757","display_name":"Afraa Sayah Alshammari","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Afraa Alshammari","raw_affiliation_strings":["University of Texas – Dallas,Department of Computer Science,Dallas,United States"],"affiliations":[{"raw_affiliation_string":"University of Texas – Dallas,Department of Computer Science,Dallas,United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115568002","display_name":"Dagmar Heintze","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dagmar Heintze","raw_affiliation_strings":["University of Texas – Dallas,School of Economic, Political and Policy Sciences,Dallas,United States"],"affiliations":[{"raw_affiliation_string":"University of Texas – Dallas,School of Economic, Political and Policy Sciences,Dallas,United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005002693","display_name":"Latifur Khan","orcid":"https://orcid.org/0000-0002-9300-1576"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Latifur Khan","raw_affiliation_strings":["University of Texas – Dallas,Department of Computer Science,Dallas,United States"],"affiliations":[{"raw_affiliation_string":"University of Texas – Dallas,Department of Computer Science,Dallas,United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107185211","display_name":"Naif Alatrush","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naif Alatrush","raw_affiliation_strings":["University of Texas – Dallas,Department of Computer Science,Dallas,United States"],"affiliations":[{"raw_affiliation_string":"University of Texas – Dallas,Department of Computer Science,Dallas,United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054154936","display_name":"Patrick T. Brandt","orcid":"https://orcid.org/0000-0002-7261-7056"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patrick T. Brandt","raw_affiliation_strings":["University of Texas – Dallas,School of Economic, Political and Policy Sciences,Dallas,United States"],"affiliations":[{"raw_affiliation_string":"University of Texas – Dallas,School of Economic, Political and Policy Sciences,Dallas,United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057729042","display_name":"Vito D\u2019Orazio","orcid":"https://orcid.org/0000-0003-4249-0768"},"institutions":[{"id":"https://openalex.org/I12097938","display_name":"West Virginia University","ror":"https://ror.org/011vxgd24","country_code":"US","type":"education","lineage":["https://openalex.org/I12097938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vito D\u2019Orazio","raw_affiliation_strings":["West Virginia University,Department of Political Science,Morgantown,United States"],"affiliations":[{"raw_affiliation_string":"West Virginia University,Department of Political Science,Morgantown,United States","institution_ids":["https://openalex.org/I12097938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057228948","display_name":"Niamat Zawad","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niamat Zawad","raw_affiliation_strings":["University of Texas – Dallas,Department of Computer Science,Dallas,United States"],"affiliations":[{"raw_affiliation_string":"University of Texas – Dallas,Department of Computer Science,Dallas,United States","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100745422","display_name":"Md. Masum Billah","orcid":"https://orcid.org/0009-0008-5448-8714"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mahrusa Billah","raw_affiliation_strings":["University of Texas – Dallas,Department of Computer Science,Dallas,United States"],"affiliations":[{"raw_affiliation_string":"University of Texas – Dallas,Department of Computer Science,Dallas,United States","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5069844991"],"corresponding_institution_ids":["https://openalex.org/I138006243"],"apc_list":null,"apc_paid":null,"fwci":0.3862,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.713303,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"542","last_page":"552"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9684000015258789,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9684000015258789,"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/T10759","display_name":"Translation Studies and Practices","score":0.9174000024795532,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6380680799484253},{"id":"https://openalex.org/keywords/politics","display_name":"Politics","score":0.6072035431861877},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5680065751075745},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.440375953912735},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.412320077419281},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.30006295442581177},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11769464612007141}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6380680799484253},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.6072035431861877},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5680065751075745},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.440375953912735},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.412320077419281},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.30006295442581177},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11769464612007141},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fllm63129.2024.10852489","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm63129.2024.10852489","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 2nd International Conference on Foundation and Large Language Models (FLLM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4301937836","https://openalex.org/W3186984283","https://openalex.org/W600256562","https://openalex.org/W2011788350","https://openalex.org/W4253914889","https://openalex.org/W1533898226","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0],"dynamics":[1,159],"of":[2,12,27,69,88,101,105,133,148,160],"political":[3,110,154,191],"conflict":[4,155],"and":[5,17,38,47,49,63,118,123,162,177,184],"cooperation":[6,18,163],"require":[7],"powerful":[8],"computerized":[9],"tools":[10],"capable":[11],"effectively":[13],"tracking":[14],"security":[15],"threats":[16],"around":[19],"the":[20,25,77,86,98,130,145,158],"world.":[21],"This":[22,54],"study":[23],"compares":[24],"performance":[26,138],"domain-specific":[28,106,150],"Large":[29],"Language":[30],"Models":[31],"(LLMs)":[32],"against":[33],"generically-trained":[34,113],"LLMs":[35,114,151,171],"in":[36,44,115,120,139],"binary":[37,122],"multi-class":[39,124],"classification":[40],"using":[41,71,165],"native":[42,166],"text":[43],"English,":[45,116],"Spanish,":[46,117],"Arabic,":[48],"their":[50,181],"corresponding":[51],"machine":[52,90,134],"translations.":[53],"endeavor":[55],"yields":[56],"four":[57],"key":[58],"contributions.":[59],"1)":[60],"We":[61,127],"present":[62],"make":[64],"available":[65],"a":[66,72,103],"novel":[67],"database":[68],"annotations":[70],"multi-lingual":[73,169],"parallel":[74],"corpus":[75],"from":[76],"United":[78],"Nations.":[79],"2)":[80],"Using":[81],"various":[82],"metrics,":[83],"we":[84],"assess":[85],"quality":[87],"different":[89,140],"translation":[91,135],"tools.":[92],"3)":[93],"Our":[94,168],"results":[95,143],"indicate":[96],"that":[97],"ConfliBERT":[99,170],"family":[100],"LLMs,":[102],"set":[104],"models":[107],"tailored":[108],"for":[109],"conflict,":[111],"outperform":[112],"Arabic":[119],"both":[121],"tasks.":[125],"4)":[126],"also":[128],"disentangle":[129],"heterogeneous":[131],"effects":[132],"on":[136,153],"LLM":[137],"languages.":[141],"Overall,":[142],"reveal":[144],"comparative":[146],"advantage":[147],"native-language":[149],"specialized":[152],"to":[156,186],"understand":[157],"violence":[161],"worldwide":[164],"text.":[167],"provide":[172],"critical":[173],"cyber-infrastructure":[174],"enabling":[175],"scholars":[176],"government":[178],"agencies":[179],"use":[180],"local":[182],"languages":[183],"information":[185],"foster":[187],"safer,":[188],"more":[189],"stable":[190],"environments.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}