{"id":"https://openalex.org/W7140323996","doi":"https://doi.org/10.48550/arxiv.2603.22288","title":"Evaluating Prompting Strategies for Chart Question Answering with Large Language Models","display_name":"Evaluating Prompting Strategies for Chart Question Answering with Large Language Models","publication_year":2026,"publication_date":"2026-03-03","ids":{"openalex":"https://openalex.org/W7140323996","doi":"https://doi.org/10.48550/arxiv.2603.22288"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.22288","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.22288","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.22288","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032780387","display_name":"Ruthuparna Naikar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naikar, Ruthuparna","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130548563","display_name":"Ying Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Ying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8077999949455261,"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":0.8077999949455261,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.026599999517202377,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.020099999383091927,"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/question-answering","display_name":"Question answering","score":0.6567999720573425},{"id":"https://openalex.org/keywords/chart","display_name":"Chart","score":0.6414999961853027},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4894999861717224},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.33809998631477356},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.3314000070095062},{"id":"https://openalex.org/keywords/affect","display_name":"Affect (linguistics)","score":0.30970001220703125}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7631000280380249},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6567999720573425},{"id":"https://openalex.org/C190812933","wikidata":"https://www.wikidata.org/wiki/Q28923","display_name":"Chart","level":2,"score":0.6414999961853027},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5839999914169312},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5680000185966492},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4894999861717224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3776000142097473},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3158000111579895},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.22288","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.22288","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.22288","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.22288","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Prompting":[0],"strategies":[1,114],"affect":[2],"LLM":[3],"reasoning":[4,118],"performance,":[5],"but":[6],"their":[7],"role":[8],"in":[9,115,127],"chart-based":[10],"QA":[11],"remains":[12],"underexplored.":[13],"We":[14],"present":[15],"a":[16],"systematic":[17],"evaluation":[18],"of":[19],"four":[20],"widely":[21],"used":[22],"prompting":[23,77,92,113],"paradigms":[24],"(Zero-Shot,":[25],"Few-Shot,":[26],"Zero-Shot":[27,96],"Chain-of-Thought,":[28],"and":[29,35,57,64,125],"Few-Shot":[30,75,91],"Chain-of-Thought)":[31],"across":[32],"GPT-3.5,":[33],"GPT-4,":[34],"GPT-4o":[36],"on":[37,45,87,103],"the":[38,53,80],"ChartQA":[39,71],"dataset.":[40],"Our":[41],"framework":[42],"operates":[43],"exclusively":[44],"structured":[46,116],"chart":[47],"data,":[48],"isolating":[49],"prompt":[50],"structure":[51],"as":[52],"only":[54,99],"experimental":[55],"variable,":[56],"evaluates":[58],"performance":[59],"using":[60],"two":[61],"metrics:":[62],"Accuracy":[63],"Exact":[65],"Match.":[66],"Results":[67],"from":[68],"1,200":[69],"diverse":[70],"samples":[72],"show":[73],"that":[74],"Chain-of-Thought":[76],"consistently":[78],"yields":[79],"highest":[81],"accuracy":[82,126],"(up":[83],"to":[84],"78.2\\%),":[85],"particularly":[86],"reasoning-intensive":[88],"questions,":[89],"while":[90],"improves":[93],"format":[94],"adherence.":[95],"performs":[97],"well":[98],"with":[100,120],"high-capacity":[101],"models":[102],"simpler":[104],"tasks.":[105],"These":[106],"findings":[107],"provide":[108],"actionable":[109],"guidance":[110],"for":[111,122],"selecting":[112],"data":[117],"tasks,":[119],"implications":[121],"both":[123],"efficiency":[124],"real-world":[128],"applications.":[129]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-26T00:00:00"}