{"id":"https://openalex.org/W4408843313","doi":"https://doi.org/10.3724/2096-7004.di.2025.0014","title":"MLLM-CTT: A Multimodal Large Language Model for Chart-to-Text Generation Based on LoRA Fine-Tuning","display_name":"MLLM-CTT: A Multimodal Large Language Model for Chart-to-Text Generation Based on LoRA Fine-Tuning","publication_year":2025,"publication_date":"2025-03-01","ids":{"openalex":"https://openalex.org/W4408843313","doi":"https://doi.org/10.3724/2096-7004.di.2025.0014"},"language":"en","primary_location":{"id":"doi:10.3724/2096-7004.di.2025.0014","is_oa":true,"landing_page_url":"https://doi.org/10.3724/2096-7004.di.2025.0014","pdf_url":"https://www.sciengine.com/doi/pdf/299D3292175A4C57A57A8DD1519647ED","source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.sciengine.com/doi/pdf/299D3292175A4C57A57A8DD1519647ED","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Kunmin Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kunmin Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101686395","display_name":"Songlin Chen","orcid":"https://orcid.org/0000-0002-2504-5630"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Songlin Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087562798","display_name":"Yajun Du","orcid":"https://orcid.org/0000-0001-5999-6699"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"YaJun Du","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100772833","display_name":"Xiaoliang Chen","orcid":"https://orcid.org/0000-0002-8201-9631"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"XiaoLiang Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02267281,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":"2","first_page":"20250014","last_page":"20250014"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9948999881744385,"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":0.9948999881744385,"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":0.9783999919891357,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9309999942779541,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/computer-science","display_name":"Computer science","score":0.7098864316940308},{"id":"https://openalex.org/keywords/chart","display_name":"Chart","score":0.6862109303474426},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5685451626777649},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4776412546634674},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46226608753204346},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11347872018814087},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06765002012252808}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7098864316940308},{"id":"https://openalex.org/C190812933","wikidata":"https://www.wikidata.org/wiki/Q28923","display_name":"Chart","level":2,"score":0.6862109303474426},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5685451626777649},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4776412546634674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46226608753204346},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11347872018814087},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06765002012252808}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3724/2096-7004.di.2025.0014","is_oa":true,"landing_page_url":"https://doi.org/10.3724/2096-7004.di.2025.0014","pdf_url":"https://www.sciengine.com/doi/pdf/299D3292175A4C57A57A8DD1519647ED","source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3724/2096-7004.di.2025.0014","is_oa":true,"landing_page_url":"https://doi.org/10.3724/2096-7004.di.2025.0014","pdf_url":"https://www.sciengine.com/doi/pdf/299D3292175A4C57A57A8DD1519647ED","source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4408843313.pdf","grobid_xml":"https://content.openalex.org/works/W4408843313.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Chart-to-text":[0],"generation":[1,17],"requires":[2],"both":[3],"strong":[4],"model":[5,163,196,218,226],"support":[6,57],"and":[7,44,72,101,133,182,201,208,236],"cross-modal":[8],"understanding":[9],"to":[10,36,67,110,128,142,164],"achieve":[11],"more":[12,228],"desirable":[13],"results.":[14],"Traditional":[15],"text":[16,132,170],"models":[18,33,52,98],"require":[19],"the":[20,29,48,56,94,112,119,123,131,139,144,148,161,166,190,204,210,220],"use":[21,138],"of":[22,58,96,114,125,169],"underlying":[23,59],"data":[24,60],"tables":[25],"in":[26,74,77,108,118],"charts.":[27,75],"On":[28,47],"one":[30],"hand,":[31,50],"these":[32,51],"often":[34],"fail":[35],"provide":[37],"critical":[38],"insights,":[39],"as":[40,62,180,184],"they":[41,63],"display":[42],"hallucinations":[43],"factual":[45],"errors.":[46],"other":[49],"overly":[53],"rely":[54],"on":[55,160,199,213],"tables,":[61],"make":[64],"it":[65],"difffcult":[66],"correctly":[68],"interpret":[69],"complex":[70],"patterns":[71],"trends":[73],"Therefore,":[76],"this":[78],"paper,":[79],"we":[80,121,137,173],"proposed":[81],"an":[82],"Multimodal":[83],"Large":[84],"Language":[85],"Model":[86],"for":[87,90,186],"Chart-to-Text":[88],"Generation(shorten":[89],"MLLM-CTT),":[91],"which":[92],"solves":[93],"problem":[95],"previous":[97],"lacking":[99],"accuracy":[100],"ffuency":[102],"through":[103],"stable":[104],"pre-training":[105],"methods.":[106],"Firstly,":[107],"order":[109],"address":[111],"issue":[113],"insufffcient":[115],"reasoning":[116],"ability":[117],"model,":[120],"introduce":[122,175],"tree":[124],"thoughts":[126],"framework":[127],"better":[129],"understand":[130],"conduct":[134],"reasoning.":[135],"Then,":[136],"Querying":[140],"Transformer(Q-Former)":[141],"align":[143],"chart":[145],"features":[146],"with":[147,230],"pre-trained":[149],"language":[150],"model.":[151],"We":[152],"perform":[153],"parallel":[154],"low":[155],"rank":[156],"adaptive":[157],"(LoRA)":[158],"ffne-tuning":[159],"MLLM-CTT":[162],"adapt":[165],"speciffc":[167],"ffelds":[168],"generation.":[171],"Finally,":[172,189],"also":[174],"some":[176],"state-of-the-art":[177,206],"models,":[178],"such":[179],"MiniGPT":[181],"LLaVA,":[183],"baselines":[185],"comparative":[187],"experiments.":[188],"evaluation":[191],"experiment":[192],"showed":[193],"that":[194,216],"our":[195,217,225],"scored":[197],"higher":[198],"BLEU":[200],"RG,":[202],"outperforming":[203],"current":[205],"systems,":[207],"had":[209],"lowest":[211],"score":[212],"PPL,":[214],"indicating":[215],"has":[219],"best":[221],"performance.":[222],"Compared":[223],"toMiniGPT-4,":[224],"is":[227],"advanced":[229],"average":[231],"improvement":[232],"rates":[233],"of7%,":[234],"4.9%,":[235],"3.17%,":[237],"respectively.":[238]},"counts_by_year":[],"updated_date":"2026-06-14T06:11:07.267592","created_date":"2025-10-10T00:00:00"}