{"id":"https://openalex.org/W4390481363","doi":"https://doi.org/10.1109/ssci52147.2023.10371906","title":"Domain-Specific Large Language Model Finetuning using a Model Assistant for Financial Text Summarization","display_name":"Domain-Specific Large Language Model Finetuning using a Model Assistant for Financial Text Summarization","publication_year":2023,"publication_date":"2023-12-05","ids":{"openalex":"https://openalex.org/W4390481363","doi":"https://doi.org/10.1109/ssci52147.2023.10371906"},"language":"en","primary_location":{"id":"doi:10.1109/ssci52147.2023.10371906","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci52147.2023.10371906","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Symposium Series on Computational Intelligence (SSCI)","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/A5059906922","display_name":"Loukia Avramelou","orcid":"https://orcid.org/0009-0000-2056-7635"},"institutions":[{"id":"https://openalex.org/I4210150023","display_name":"Computational Intelligence and Information Systems Lab","ror":"https://ror.org/04fqqys39","country_code":"AR","type":"facility","lineage":["https://openalex.org/I4210150023"]}],"countries":["AR"],"is_corresponding":true,"raw_author_name":"Loukia Avramelou","raw_affiliation_strings":["Computational Intelligence and Deep Learning Group,AIIA Lab","AIIA Lab, Computational Intelligence and Deep Learning Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Intelligence and Deep Learning Group,AIIA Lab","institution_ids":["https://openalex.org/I4210150023"]},{"raw_affiliation_string":"AIIA Lab, Computational Intelligence and Deep Learning Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061050264","display_name":"Nikolaos Passalis","orcid":"https://orcid.org/0000-0003-1177-9139"},"institutions":[{"id":"https://openalex.org/I4210150023","display_name":"Computational Intelligence and Information Systems Lab","ror":"https://ror.org/04fqqys39","country_code":"AR","type":"facility","lineage":["https://openalex.org/I4210150023"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Nikolaos Passalis","raw_affiliation_strings":["Computational Intelligence and Deep Learning Group,AIIA Lab","AIIA Lab, Computational Intelligence and Deep Learning Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Intelligence and Deep Learning Group,AIIA Lab","institution_ids":["https://openalex.org/I4210150023"]},{"raw_affiliation_string":"AIIA Lab, Computational Intelligence and Deep Learning Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026561247","display_name":"Grigorios Tsoumakas","orcid":"https://orcid.org/0000-0002-7879-669X"},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Grigorios Tsoumakas","raw_affiliation_strings":["Aristotle University of Thessaloniki,Intelligent Systems Laboratory,Department of Informatics,Thessaloniki,Greece","Department of Informatics, Intelligent Systems Laboratory, Aristotle University of Thessaloniki, Thessaloniki, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aristotle University of Thessaloniki,Intelligent Systems Laboratory,Department of Informatics,Thessaloniki,Greece","institution_ids":["https://openalex.org/I21370196"]},{"raw_affiliation_string":"Department of Informatics, Intelligent Systems Laboratory, Aristotle University of Thessaloniki, Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041054091","display_name":"Anastasios Tefas","orcid":"https://orcid.org/0000-0003-1288-3667"},"institutions":[{"id":"https://openalex.org/I4210150023","display_name":"Computational Intelligence and Information Systems Lab","ror":"https://ror.org/04fqqys39","country_code":"AR","type":"facility","lineage":["https://openalex.org/I4210150023"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Anastasios Tefas","raw_affiliation_strings":["Computational Intelligence and Deep Learning Group,AIIA Lab","AIIA Lab, Computational Intelligence and Deep Learning Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Intelligence and Deep Learning Group,AIIA Lab","institution_ids":["https://openalex.org/I4210150023"]},{"raw_affiliation_string":"AIIA Lab, Computational Intelligence and Deep Learning Group","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059906922"],"corresponding_institution_ids":["https://openalex.org/I4210150023"],"apc_list":null,"apc_paid":null,"fwci":0.6809,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76898989,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"381","last_page":"386"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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/T10028","display_name":"Topic Modeling","score":1.0,"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":0.9991000294685364,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9876999855041504,"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/automatic-summarization","display_name":"Automatic summarization","score":0.9701669812202454},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8362143039703369},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.583081841468811},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5388851165771484},{"id":"https://openalex.org/keywords/multi-document-summarization","display_name":"Multi-document summarization","score":0.4689091444015503},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4553010165691376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45112767815589905},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.45073121786117554},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4339163601398468},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.42972007393836975},{"id":"https://openalex.org/keywords/paragraph","display_name":"Paragraph","score":0.42193371057510376},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2249716818332672}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9701669812202454},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8362143039703369},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.583081841468811},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5388851165771484},{"id":"https://openalex.org/C134714966","wikidata":"https://www.wikidata.org/wiki/Q6934448","display_name":"Multi-document summarization","level":3,"score":0.4689091444015503},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4553010165691376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45112767815589905},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.45073121786117554},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4339163601398468},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.42972007393836975},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.42193371057510376},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2249716818332672},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ssci52147.2023.10371906","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci52147.2023.10371906","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2110693578","https://openalex.org/W2896457183","https://openalex.org/W2963929190","https://openalex.org/W2970419734","https://openalex.org/W3034999214","https://openalex.org/W4205807230","https://openalex.org/W4294975662","https://openalex.org/W4379528164","https://openalex.org/W6631501603","https://openalex.org/W6682631176","https://openalex.org/W6755207826","https://openalex.org/W6769311223","https://openalex.org/W6771915120","https://openalex.org/W6793886675"],"related_works":["https://openalex.org/W3164984162","https://openalex.org/W2104677027","https://openalex.org/W2902627734","https://openalex.org/W2112885393","https://openalex.org/W2173208124","https://openalex.org/W2568827738","https://openalex.org/W1990695371","https://openalex.org/W2365100044","https://openalex.org/W2099859325","https://openalex.org/W2474342320"],"abstract_inverted_index":{"The":[0,244],"financial":[1,14,34,46],"market":[2,15,47],"and":[3,23,42,55,68,117,142,255],"public":[4,21,26],"opinion":[5,22,27],"are":[6,146],"cor-related.":[7],"This":[8,106],"means":[9],"that":[10,108],"changes":[11,19,24,31],"in":[12,18,30,78,83,160,192,234,237],"the":[13,33,45,62,98,185,200],"can":[16,28,87,139,165],"result":[17,29,60],"to":[20,25,32,48,93],"market.":[35],"Accordingly,":[36],"it":[37],"is":[38,124,247],"essential":[39,135],"for":[40,90,113,182,213,263],"understanding":[41],"interacting":[43],"with":[44],"gather":[49],"text":[50,122,132,148,156,189,216,231,252,264],"content":[51],"from":[52],"online":[53,70],"sources":[54],"process":[56],"it.":[57],"As":[58],"a":[59,91,125,161,180,188,193,210,222,250],"of":[61,65,101,127,131,187,202,215],"rapid":[63],"growth":[64],"social":[66],"media":[67],"other":[69],"sources,":[71],"we":[72,109,169,178,208,239],"have":[73],"seen":[74],"an":[75,154],"exponential":[76],"rise":[77],"data,":[79,82,145],"particularly":[80],"textual":[81,115,144],"recent":[84],"years.":[85],"It":[86],"be":[88,166],"difficult":[89],"person":[92],"read,":[94],"let":[95],"alone":[96],"process,":[97],"massive":[99],"volumes":[100],"data":[102,116],"generated":[103],"every":[104],"day.":[105],"indicates":[107],"need":[110],"automated":[111,155],"methods":[112],"processing":[114],"extracting":[118],"useful":[119],"information.":[120,136],"Automated":[121],"summarization":[123,149,157,173,190,217,232,242,253],"method":[126,212,246],"shortening":[128],"huge":[129],"amounts":[130],"without":[133,199],"losing":[134],"Transformers,":[137],"which":[138,219,225,238],"efficiently":[140],"manage":[141],"analyze":[143],"state-of-the-art":[147],"models.":[150],"However,":[151],"developing":[152],"such":[153],"model":[158,191,223],"specialized":[159],"domain":[162,227],"(e.g.":[163],"finance)":[164],"challenging":[167],"since":[168],"lack":[170,240],"necessary":[171],"domain-specific":[172],"datasets.":[174,243],"In":[175],"this":[176,206],"work,":[177],"propose":[179],"pipeline":[181],"fully":[183],"automating":[184],"finetuning":[186,230],"specific":[194,235],"domain,":[195,198],"namely":[196],"cryptocurrency":[197],"involvement":[201],"human":[203],"annotators.":[204],"To":[205],"end,":[207],"introduce":[209],"novel":[211],"self-improvement":[214],"models":[218,233],"relies":[220],"on":[221,249],"assistant":[224],"encodes":[226],"knowledge,":[228],"enabling":[229],"domains":[236],"specific-domain":[241],"proposed":[245],"evaluated":[248],"cryptocurrency-related":[251],"problem":[254],"three":[256],"well-known":[257],"Large":[258],"Language":[259],"Models":[260],"(LLMs)":[261],"used":[262],"summarization.":[265]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2025-10-10T00:00:00"}