{"id":"https://openalex.org/W7202322126","doi":null,"title":"Investigating the effect of Input Modality on Reasoning in VLMs using Zero-shot evaluation","display_name":"Investigating the effect of Input Modality on Reasoning in VLMs using Zero-shot evaluation","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W7202322126"},"language":"en","primary_location":{"id":"pmh:oai:digitalcommons.usf.edu:bcreus-1024","doi":null,"is_oa":true,"landing_page_url":"https://digitalcommons.usf.edu/bcreus/2026/spring/12","pdf_url":"https://digitalcommons.usf.edu/context/bcreus/article/1024/viewcontent/group5_5231221_213126880_Investigating_the_Effect_of_Input_Modality_on_Reasoning_in_VLMs_Using_Zero_shot_Evaluation.pdf","source":{"id":"https://openalex.org/S4377196272","display_name":"Digital Commons - University of South Florida (University of South Florida)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2613432","host_organization_name":"University of South Florida","host_organization_lineage":["https://openalex.org/I2613432"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bellini College REU Symposium (BCREUS)","raw_type":"text"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://digitalcommons.usf.edu/context/bcreus/article/1024/viewcontent/group5_5231221_213126880_Investigating_the_Effect_of_Input_Modality_on_Reasoning_in_VLMs_Using_Zero_shot_Evaluation.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5147050946","display_name":"Rodela Ghosh","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2613432","display_name":"University of South Florida","ror":"https://ror.org/032db5x82","country_code":"US","type":"education","lineage":["https://openalex.org/I2613432"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ghosh, Rodela","raw_affiliation_strings":["University of South Florida"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of South Florida","institution_ids":["https://openalex.org/I2613432"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147011926","display_name":"Aviral Gupta","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2613432","display_name":"University of South Florida","ror":"https://ror.org/032db5x82","country_code":"US","type":"education","lineage":["https://openalex.org/I2613432"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gupta, Aviral","raw_affiliation_strings":["University of South Florida"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of South Florida","institution_ids":["https://openalex.org/I2613432"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014340264","display_name":"Ocean Monjur","orcid":"https://orcid.org/0000-0003-1526-6808","observed_orcids":["https://orcid.org/0000-0003-1526-6808"]},"institutions":[{"id":"https://openalex.org/I2613432","display_name":"University of South Florida","ror":"https://ror.org/032db5x82","country_code":"US","type":"education","lineage":["https://openalex.org/I2613432"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Monjur, Ocean","raw_affiliation_strings":["University of South Florida"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of South Florida","institution_ids":["https://openalex.org/I2613432"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140696573","display_name":"Shrestha Datta","orcid":"https://orcid.org/0009-0000-8375-9423","observed_orcids":["https://orcid.org/0009-0000-8375-9423"]},"institutions":[{"id":"https://openalex.org/I2613432","display_name":"University of South Florida","ror":"https://ror.org/032db5x82","country_code":"US","type":"education","lineage":["https://openalex.org/I2613432"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Datta, Shrestha","raw_affiliation_strings":["University of South Florida"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of South Florida","institution_ids":["https://openalex.org/I2613432"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5127974620","display_name":"Anshuman Chhabra","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2613432","display_name":"University of South Florida","ror":"https://ror.org/032db5x82","country_code":"US","type":"education","lineage":["https://openalex.org/I2613432"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chhabra, Anshuman","raw_affiliation_strings":["University of South Florida"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of South Florida","institution_ids":["https://openalex.org/I2613432"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2613432"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.00039999998989515007,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.00019999999494757503,"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/vision-language-models","display_name":"vision-language models","score":0.9259999990463257},{"id":"https://openalex.org/keywords/mathematical-reasoning","display_name":"mathematical reasoning","score":0.8169999718666077},{"id":"https://openalex.org/keywords/input-modality","display_name":"input modality","score":0.9829999804496765},{"id":"https://openalex.org/keywords/rendered-images","display_name":"rendered images","score":0.47699999809265137},{"id":"https://openalex.org/keywords/gsm8k","display_name":"GSM8K","score":0.8420000076293945},{"id":"https://openalex.org/keywords/llava","display_name":"LLaVA","score":0.972000002861023},{"id":"https://openalex.org/keywords/zero-shot-evaluation","display_name":"zero-shot evaluation","score":0.7450000047683716},{"id":"https://openalex.org/keywords/multimodal-reasoning","display_name":"multimodal reasoning","score":0.4090000092983246}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7085000276565552},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.636900007724762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6089000105857849},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5695000290870667},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5379999876022339},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5051000118255615},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4050999879837036},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38280001282691956},{"id":"https://openalex.org/C19479481","wikidata":"https://www.wikidata.org/wiki/Q6888033","display_name":"Modality effect","level":5,"score":0.37869998812675476},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.31940001249313354},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2732999920845032},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.25279998779296875},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:digitalcommons.usf.edu:bcreus-1024","doi":null,"is_oa":true,"landing_page_url":"https://digitalcommons.usf.edu/bcreus/2026/spring/12","pdf_url":"https://digitalcommons.usf.edu/context/bcreus/article/1024/viewcontent/group5_5231221_213126880_Investigating_the_Effect_of_Input_Modality_on_Reasoning_in_VLMs_Using_Zero_shot_Evaluation.pdf","source":{"id":"https://openalex.org/S4377196272","display_name":"Digital Commons - University of South Florida (University of South Florida)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2613432","host_organization_name":"University of South Florida","host_organization_lineage":["https://openalex.org/I2613432"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bellini College REU Symposium (BCREUS)","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:digitalcommons.usf.edu:bcreus-1024","doi":null,"is_oa":true,"landing_page_url":"https://digitalcommons.usf.edu/bcreus/2026/spring/12","pdf_url":"https://digitalcommons.usf.edu/context/bcreus/article/1024/viewcontent/group5_5231221_213126880_Investigating_the_Effect_of_Input_Modality_on_Reasoning_in_VLMs_Using_Zero_shot_Evaluation.pdf","source":{"id":"https://openalex.org/S4377196272","display_name":"Digital Commons - University of South Florida (University of South Florida)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2613432","host_organization_name":"University of South Florida","host_organization_lineage":["https://openalex.org/I2613432"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bellini College REU Symposium (BCREUS)","raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W7202322126.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416951116","https://openalex.org/W7154984670","https://openalex.org/W7125380444","https://openalex.org/W4404350777","https://openalex.org/W7083832184","https://openalex.org/W7213783732","https://openalex.org/W6929657348","https://openalex.org/W4417166485","https://openalex.org/W4416441295","https://openalex.org/W6910630806"],"abstract_inverted_index":{"This":[0],"project":[1],"investigates":[2],"how":[3],"input":[4,51],"modality":[5,33,74],"affects":[6],"mathematical":[7],"reasoning":[8,98],"in":[9,75,99],"vision-language":[10],"models":[11,44,70],"(VLMs).":[12],"Using":[13],"100":[14],"samples":[15],"from":[16,55,61],"the":[17,66,72],"GSM8K":[18],"benchmark,":[19],"we":[20],"evaluate":[21],"Qwen2-VL-2B-Instruct":[22],"and":[23,31,38,59,108],"LLaVA-v1.6-Mistral-7B":[24],"across":[25],"three":[26],"conditions:":[27],"text-only,":[28],"rendered":[29],"image,":[30],"a":[32],"mismatch":[34,67],"condition":[35],"where":[36],"image":[37],"text":[39,73,82],"describe":[40],"different":[41],"problems.":[42],"Both":[43],"show":[45],"substantial":[46],"accuracy":[47],"drops":[48],"under":[49],"visual":[50,104],"\u2014":[52],"Qwen2":[53],"falls":[54],"55%":[56],"to":[57,63],"30%":[58],"LLaVA":[60],"40%":[62],"21%.":[64],"In":[65],"condition,":[68],"both":[69],"follow":[71],"over":[76],"75%":[77],"of":[78],"cases,":[79],"revealing":[80],"strong":[81],"dominance":[83],"when":[84,103],"modalities":[85],"conflict.":[86],"These":[87],"findings":[88],"suggest":[89],"that":[90],"rendering":[91],"math":[92],"problems":[93],"as":[94],"images":[95],"meaningfully":[96],"impairs":[97],"current":[100],"VLMs,":[101],"even":[102],"content":[105],"is":[106],"clean":[107],"legible.":[109]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-13T00:00:00"}
